Methods and Systems for Collaborative Orchestration by Agents

This application is a continuation of U.S. application Ser. No. 19/204,316, filed May 9, 2025, which claims priority to U.S. Provisional App. No. 63/742,320, filed Jan. 6, 2025, each of which is hereby incorporated by reference in its entirety.

The disclosed embodiments relate generally to artificial intelligence platforms, and, in particular, to managing agents for processing tasks.

Information technology (IT) systems (e.g., within cloud platforms) are rapidly growing in complexity and scale (e.g., due to relentless cybersecurity threats, exponentially increased customer demands for new features, etc.). This growth brings increased challenges while simultaneously enhancing system power and flexibility.

Existing IT systems encounter several concerns. A first concern is related to operational inefficiencies. Specifically, the exponential growth and complexity of cloud systems result in increased management challenges and rising costs, prolonged mean time to repair (MTTR) for resolving issues, and extensive time for root cause analysis (RCA), collectively impacting service quality. A second concern is related to the limitations of human-only teams. Specifically, the rapid pace of changes in existing IT systems surpasses human capabilities, leading to reduced productivity, skill and speed constraints, increased human errors, elevated stress levels and burnout, and an inability to meet growing demands. A third concern is related to the imperative for innovation.

The explosive growth of cloud technology makes IT systems more complex yet immensely powerful and flexible. For example, cloud environments of a service entity (e.g., a company for information service, technology service, network service, and/or other types of services) may experience exponential growth to support increasing service demands. Various of embodiments are directed to methods and systems for providing an agentic orchestration platform based on an agentic system that allows agents to dynamically, autonomously, and adaptively solve tasks (e.g., critical and high-priority incidents) associated with service demands. In particular, the agentic system accelerates operational efficiencies, e.g., delegating complex tasks to autonomous artificial intelligence (AI) agents under supervision, increasing productivity across various business and IT processes, decreasing mean time to repair (MTTR), and decreasing time to perform RCA root cause analysis (RCA). Moreover, the agentic system unlocks human potential through AI, e.g., exponentially enhancing productivity across various functions (e.g., ITs, finance, businesses, etc.), accelerating process by augmenting human teams with using AI agents, delighting consumers and customers by creating a stress-free experience, and boosting the capability meet and exceed growing demands. Additionally, the agentic system revolutionizes cloud technologies and markets for IT systems, e.g., bring AI augmentation across various business units, infrastructure, and applications, achieving streamlined operations that drives cost reduction and enhances efficiencies for both internal operations and customers, and leveraging AI and automation for optimizing IT resources.

In accordance with some embodiments, a method is provided. A method of orchestrating agents for a user task includes generating, based on a user request and by a first agent, a workflow. The workflow includes a plurality of steps. The method further includes generating, based on the workflow and by a second agent, one or more on-demand agents. Each of the plurality of steps is assigned to a respective on-demand agent of the one or more on-demand agents. The method further includes analyzing the workflow by the one or more on-demand agents to generate output data. The method further includes receiving user supervision associated with the output data by the first agent. The method further includes determining, based on the user supervision and by the second agent, whether the output data requires updating. The method further includes in accordance with a determination that the output data requires updating, updating the output data. The method further includes displaying the updated output data to a user. Each agent of the first agent, the second agent, and the one or more on-demand agents is driven by a respective computational component from a plurality of computational components.

In accordance with some embodiments, a method is provided. A method of orchestrating artificial intelligence agents for a user task includes instantiating, based on a request from a user and by an external interface artificial intelligence agent, a workflow. The workflow includes a plurality of steps configured to resolve a critical computing event. The method further includes instantiating, based on the workflow and by an internal orchestrating artificial intelligence agent, one or more on-demand artificial intelligence agents. The method further includes executing the workflow by the one or more on-demand artificial intelligence agents to generate output data for the internal orchestrating artificial intelligence agent. Executing the workflow includes, for each of the plurality of steps: assigning a respective step to a respective on-demand artificial intelligence agent of the one or more on-demand artificial intelligence agents; and executing, by the respective on-demand artificial intelligence agent, the respective step to generate respective data. The method further includes transmitting, by the internal orchestrating artificial intelligence agent, the output data to the external interface artificial intelligence agent. The method further includes displaying, by the external interface artificial intelligence agent, the output data to the user. The method further includes receiving user supervision corresponding to the critical computing event and the output data. The method further includes transmitting, by the external interface artificial intelligence agent, the user supervision to the internal orchestrating artificial intelligence agent. The method further includes determining, based on the user supervision and by the internal orchestrating artificial intelligence agent, whether the output data requires updating. The method further includes in accordance with a determination that the output data requires updating, updating, by the one or more on-demand artificial intelligence agents, the output data to generate updated output data for the internal orchestrating artificial intelligence agent. The method further includes transmitting, by the internal orchestrating artificial intelligence agent, the updated output data to the external interface artificial intelligence agent. The method further includes displaying, by the external interface artificial intelligence agent, the updated output data to the user. Each artificial intelligence agent of the external interface artificial intelligence agent, the internal orchestrating artificial intelligence agent, and the one or more on-demand artificial intelligence agents is distinct from every other artificial intelligence agent and includes a large-language model.

In accordance with some embodiments, a method is provided. A method of orchestrating agents for resolving incidents includes receiving, from a user, an incident defining a target issue to be addressed. The method further includes convening in real-time, based on the incident and by a coordinating agent, a call that defines a collaboration. The method further includes dynamically spawning, using computational resources, one or more on-call agents corresponding to the collaboration. The method further includes generating, by the one or more on-call agents, output data. The method further includes transmitting the output data to the user. The method further includes automatically terminating the one or more on-call agents by releasing the computational resources.

In accordance with some embodiments, a method is provided. A method of orchestrating artificial intelligence agents for resolving incidents includes receiving, from a user, a critical computing incident defining a target issue to be addressed. The method further includes instantiating in real-time, based on the critical computing incident and by an interface coordinating artificial intelligence agent, a call that defines a collaboration. The method further includes dynamically allocating a set of computational resources from a pool of computational resources to the collaboration. The method further includes dynamically spawning, using the set of computational resources, one or more on-call artificial intelligence agents corresponding to the collaboration. The method further includes generating, by the one or more on-call artificial intelligence agents, output data. The method further includes transmitting the output data to the user. The method further includes automatically monitoring a usage status of the pool of computational resources. The method further includes automatically terminating, based on the usage status, the one or more on-call artificial intelligence agents by releasing the set of computational resources. Each artificial intelligence agent of the interface coordinating artificial intelligence agent and the one or more on-call artificial intelligence agents is distinct from every other artificial intelligence agent and includes a large-language model.

In accordance with some embodiments, a method is provided. A method of orchestrating agents for resolving incidents includes receiving, by an interface agent and via a web user interface, a first user query from a user that defines a request to summarize historical data corresponding to a critical event associated with a plurality of incidents. The method further includes in response to receiving the first user query, generating, by an executing agent, an event report associated with the critical event. The method further includes displaying, by the interface agent and via the web user interface, the event report to the user. The method further includes receiving, by the interface agent and via the web user interface, a second user query from the user that defines a request to reduce a mean time to repair (MTTR) for resolving the critical event. The method further includes in response to receiving the second user query, generating, by the executing agent, an enhanced standard operating procedure (SOP) configured to reduce the MTTR for resolving the critical event. The method further includes displaying, by the interface agent and via the web user interface, the enhanced SOP to the user.

In accordance with some embodiments, a method is provided. A method of orchestrating artificial intelligence agents for self-service includes receiving, by an interface artificial intelligence agent and via a web user interface, a first user query from a user that defines a request to summarize historical data corresponding to a critical computing event associated with a plurality of computing incidents. The method further includes in response to receiving the first user query, generating, by an executing artificial intelligence agent, an event report associated with the critical computing event. The method further includes displaying, by the interface artificial intelligence agent and via the web user interface, the event report to the user. The method further includes in response to receiving the second user query, generating, by the executing artificial intelligence agent, an enhanced standard operating procedure (SOP) configured to reduce the MTTR for resolving the critical computing event. The method further includes displaying, by the interface artificial intelligence agent and via the web user interface, the enhanced SOP to the user. Each artificial intelligence agent of the interface coordinating artificial intelligence agent and the one or more on-call artificial intelligence agents is distinct from every other artificial intelligence agent and includes a large-language model.

In accordance with some embodiments, a computer system is provided. The computer system includes one or more processors and memory storing one or more programs. The one or more programs are configured to be executed by the one or more processors. The one or more programs include instructions for performing any of the methods described herein.

In accordance with some embodiments, a non-transitory computer-readable storage medium is provided. The one or more programs comprises instructions that, when executed by a computer system that includes one or more processors, cause the one or more processors to perform operations for any of the methods described herein.

These illustrative aspects are mentioned not to limit or define the disclosure, but to provide examples to aid understanding thereof. Additional embodiments are discussed in the Detailed Description, and further description is provided there.

Reference will now be made to embodiments, examples of which are illustrated in the accompanying drawings. In the following description, numerous specific details are set forth in order to provide an understanding of the various described embodiments. However, it will be apparent to one of ordinary skill in the art that the various described embodiments may be practiced without these specific details. In other instances, well-known methods, procedures, components, circuits, and networks have not been described in detail so as not to unnecessarily obscure aspects of the embodiments.

It will also be understood that, although the terms first, second, etc. are, in some instances, used herein to describe various elements, these elements should not be limited by these terms. These terms are used only to distinguish one element from another. For example, a first widget could be termed a second widget, and, similarly, a second widget could be termed a first widget, without departing from the scope of the various described embodiments. The first widget and the second widget are both widgets, but they are not the same widget.

The terminology used in the description of the various embodiments described herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used in the description of the various described embodiments and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and/or” as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. It will be further understood that the terms “includes,” “including,” “comprises,” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

As used herein, the term “if” is, optionally, construed to mean “when” or “upon” or “in response to determining” or “in response to detecting” or “in accordance with a determination that,” depending on the context. Similarly, the phrase “if it is determined” or “if [a stated condition or event] is detected” is, optionally, construed to mean “upon determining” or “in response to determining” or “upon detecting [the stated condition or event]” or “in response to detecting [the stated condition or event]” or “in accordance with a determination that [a stated condition or event] is detected,” depending on the context.

The explosive growth of cloud technology makes IT systems more complex yet immensely powerful and flexible. For example, cloud environments of a service entity (e.g., a company for information service, technology service, network service, and/or other types of services) may experience exponential growth to support increasing service demands. In some circumstances, the exponential growth of the cloud environments is manifested as the utilization of hundreds or thousands of cloud accounts across various cloud computing platforms to deliver services to customers, with a growth rate of approximately 20-30% annually or 2-3% monthly. In particular, IT systems continue to encounter a significant volume of critical and high-priority incidents (e.g., hundreds or thousands of incidents annual). Accordingly, resolving these incidents is intensive, requiring an estimated 20-50 days to address every 100 critical and high-priority incidents.

100 102 150 350 352 552 1 FIG. 1 FIG. 1 FIG. 3 FIG. 5 FIG.B Various of embodiments presented in this application are directed to methods and systems for providing an agentic orchestration platform (e.g., agentic orchestration platformin) based on an agentic system (e.g., agentic systemin) that allows agents to dynamically, autonomously, and adaptively solve tasks (e.g., resolving critical and high-priority incidents). In some embodiments, the agents (e.g., agentin, agentand agentin, agentin) of the agentic system are AI agents driven by computational components (e.g., analytical models, machine-learning models, large-language models (LLMs), plugins, other types of models, or a combination of various types). In some embodiments, the agentic system operates under supervision (e.g., user supervision, user input, user interception, etc.) and is configured to provide ethical decision-making and adaptability in complex, dynamic environments.

Various of embodiments presented in this application may offer the advantages including, but not limited to, enhancing operational efficiency, surpassing human limitations with AI augmentation, and providing hardware improvements for IT system infrastructure.

102 1 FIG. First, the agentic system (e.g., agentic systemin) enhances operational efficiency by assisting application & business owners, IT development, security & operations, and incident & problem management, with respect to (i) automated solutions for repetitive and time-consuming tasks, (ii) quick, concise, and actionable insights, (iii) minimal need for constant manual intervention, (iv) enhanced system reliability and performance, and (v) retaining human oversight for critical decisions. In particular, the agentic system resolves significant challenges including (i) reduced organizational efficiency due to the inability to remediate at scale and (ii) increased downtime during incidents which have financial, regulatory, and legal consequences. Moreover, the agentic system addresses several issues including (i) slow-down of manual processes, (ii) high operational costs due to excessive manpower, (iii) increased workload from handling repetitive tasks that lead to potential burnout for humans, and (iv) delays in incident resolution leading to severe financial and regulatory risks. For example, a critical and high-priority incident may require an IT system to run vulnerability detection scripts on over tens of thousands (e.g., 10,000 to 50,000) of computer servers globally, incurring a significant financial and manpower cost. In another example, an unplanned application outage would make an IT service company encounter a few hours of unplanned downtime per week, leading to significant impacts on IT systems (e.g., system operations) and customer experiences (e.g., user satisfaction). In this situation, the agentic system can be implemented to automate and optimize error detection, at-scale remediation, and incident management, which are crucial to improve operational efficiency and reduce downtime and cost (e.g., on manpower, finance, etc.).

102 1 FIG. Second, the agentic system (e.g., agentic systemin) surpasses human limitations by leveraging AI to augment and execute tasks (e.g., for operations in IT systems). For example, in some embodiments, the agentic system implements agents (e.g., AI agents) that are driven by computational components (e.g., data analytics, analytical models, machine-learning models, LLMs, plugins, other types of models, or a combination of various types) and configured as an integrated multi-agent framework. In particular, the integrated multi-agent framework is configured to reason, learn, execute tasks, and make decisions while communicating and collaborating internally (e.g., between agents) and externally (e.g., with humans/users) to solve tasks (e.g., critical and high-priority incidents, user requests, user queries). Specifically, in some embodiments, the agentic system receives supervision (e.g., user supervision, user input, user interception) to make more effective decisions and ensure safety and accuracy. Additionally, the AI augmentation also enhances the agentic system's capabilities with respect to (i) automating IT operations by eliminating inefficiencies and excessive costs (e.g., manpower), (ii) offering versatility and adaptation across various applications (e.g., Software as a Service (SaaS), IT operations, back-office systems, etc.) processes (e.g., decision-makings, optimizations, etc.), and (iii) boosting productivity by freeing human teams from repetitive tasks.

102 104 104 1 FIG. 1 FIG. Third, the agentic system (e.g., agentic systemin) provides hardware improvements for IT system infrastructure. For example, the agentic system can optimize hardware utilization, e.g., monitoring hardware performance in real-time and ensuring optimal usage by dynamically allocating resources (e.g., resource of functional platformsin) based on real-time demands of tasks (e.g., critical and high-priority incidents). In another example, the agentic system can optimize hardware configurations for IT system infrastructure, e.g., tuning hardware components (e.g., allocation of databases, memory, computing devices) of an IT system for peak performance, adjusting workloads and identifying inefficiencies within hardware components that slow operations, and extending lifespan hardware components by evenly distributing workloads. In yet another example, the agentic system can perform legacy leapfrogging (e.g., bypassing outdated infrastructure for immediate advancements). In yet another example, the agentic system optimizes the utilization of system resources (e.g., resources in the plurality of functional platforms) by dynamically monitoring workloads and efficiently releasing resources that are no longer needed (e.g., releasing an agent that was earlier created but is no longer needed).

1 FIG. 100 102 100 102 104 102 104 104 is a block diagram illustrating an agentic orchestration platformincluding an agentic system, in accordance with some embodiments. The agentic orchestration platformincludes the agentic systemand a plurality of functional platforms. The agentic systemis configured to bidirectionally communicate with the plurality of functional platformsfor receiving data (e.g., tasks, requests, inputs), sending data (e.g., results, documentations), managing resources (e.g., storages, computing resources, training powers, etc.), and integrating functionalities (e.g., coordinating multiple resources between the plurality of functional platforms).

104 100 106 108 110 112 114 116 118 120 In some embodiments, the plurality of functional platformsof the agentic orchestration platforminclude, but are not limited to a user platform(e.g., service centers, user/task management systems, content delivery networks, etc.), an AI platform(e.g., machine learning operations, model training frameworks, natural language processing, etc.), a database platform(e.g., data storage devices, database management systems, relational databases, data warehouses, data lakes, etc.), a cloud platform(Infrastructure as a Service, Platform as a Service, serverless computing resources, etc.), a computing platform(e.g., operating systems, virtual machines, containerization platforms, etc.), a device platform(e.g., device terminals, workstations, applications, mobile operation systems, embedded systems, internet-of-thing platforms, etc.), a documentation platform(e.g., documentation controls, editors, documentation related software, etc.), and a user interface (UI) platform(e.g., web applications, UI component libraries, cross-platform UI toolkits, etc.).

102 100 150 150 1 150 150 130 106 140 130 140 132 132 130 150 104 150 1 108 150 110 150 104 150 1 150 150 2 150 150 150 1 106 130 140 130 130 132 132 150 1 150 104 150 2 108 112 114 k k In some embodiments, the agentic systemof the agentic orchestration platformincludes a plurality of agents(e.g., agent-to agent-, where k is an integer greater than two). In some embodiments, the plurality of agentsreceive a task(e.g., a user request, a user query, a critical and high-priority incident) from a user (e.g., a user/human of the user platform), generate a workflowbased on the task, analyze the workflowto obtain a result, and send the resultto the user. In particular, when processing the task, the plurality of agentsutilize various resources provided by the plurality of functional platforms. For example, a respective agent (e.g., agent-) communicates with the AI platformto access machine learning models, LLMs, and/or computing powers for neural networks. In another example, the plurality of agentsreceive data from (e.g., historical incidents, standard of procedures (SOPs)) and store data (e.g., new incidents, updated SOPs) to the database platform. In yet another example, one or more agents of the plurality of agentsare dynamically created (e.g., on an as-needed basis, on-demand) using resources provided in the plurality of functional platforms. In some embodiments, a respective agent (e.g., agent-) of the plurality of agentsis a central agent and remaining agents (e.g., agents-to-) of the plurality of agentsare non-central agents. For example, the central agent (e.g., agent-) is configured to communicate externally with the user (e.g., via the user platform) to receive the task, generate the workflowbased on the task, coordinate (e.g., orchestrate) the non-central agents to analyze the taskto generate the result, and send the resultto the user. In another example, the central agent (e.g., agent-) dynamically creates one or more agents of the plurality of agentsusing a combination of resources provided in the plurality of functional platforms(e.g., creating a respective agent-on demand using resources provided by the AI platform, the cloud platform, and the computing platform).

102 150 130 102 150 130 102 150 110 118 102 150 512 140 130 106 102 130 150 1 150 2 106 102 130 150 1 134 140 5 FIG.B In some embodiments, the agentic systemis configured to dynamically create (e.g., on an as-needed basis, on-demand) one or more agents of the plurality of agentsto augment human capabilities (e.g., for resolving critical and high-priority incidents, handling complex, time-consuming tasks), allowing human teams to focus on more strategic work. For example, in response to the task(e.g., a user request for customer service(s)), the agentic systemcreates the plurality of agentsto form a chatbot for customer service. In another example, in response to the task(e.g., a user query for SOPs), the agentic systemcreates the plurality of agentsto access existing SOPs for incidents via the database platformand/or the documentation platformand generate a software script that summarizes the existing SOPs. In some embodiments, the agentic systemis configured to assemble the plurality of agentsas a pipeline (e.g., second pipelinein) corresponding to the workflowand form an automated process of analyzing the taskreceived from a user (e.g., via the user platform). In some embodiments, when the agentic systemanalyzes the task, a respective agent (e.g., agent-) is configured to call another respective agent (e.g., agent-) and exchanges messages and/or to request user input(s) (e.g., via the user platform). In some embodiments, when the agentic systemanalyzes the task, a respective agent (e.g., agent-) is configured to receive (e.g., wait for) supervision(e.g., user supervision, user input, user interception, etc.) prior to proceeding to a next step subsequent to a current step of a plurality steps associated with the workflow.

102 100 102 100 106 108 112 120 102 116 106 108 110 112 116 120 150 102 In some embodiments, the agentic systemof the agentic orchestration platformincludes an embedded agentic system. In some embodiments, the embedded agentic system is configured as one of the modalities of the agentic system. In some embodiments, the embedded agentic system is developed by a software development kit (SDK) configured as an integrated interface (e.g., command line interface (CLI)) to support application programming interface (API) calls. In some embodiments, the embedded agentic system is extensible across internal/external business and internet processes to perform complex tasks (e.g., for a service company). In some embodiments, the embedded agentic system is configured to be a standalone package (e.g., a self-contained software module) included in the agentic orchestration platform. In some embodiments, the embedded agentic system is configured to incorporate AI functionalities (e.g., via the user platform, the AI platform, the cloud platform, and/or the UI platform) into new or existing applications (e.g., applications that drive the agentic system, applications of the device platform). In some embodiments, the embedded agentic system includes one or more plugins that allows new skills and functionalities (e.g., obtained via the user platform, the AI platform, the database platform, the cloud platform, the device platform, and/or the UI platform) be added into the plurality of agentsof the agentic system.

102 100 140 130 150 102 140 108 110 118 102 104 150 150 104 106 108 110 112 114 116 118 120 150 150 150 150 102 130 130 132 3 6 FIGS.- In some embodiments, the agentic systemof the agentic orchestration platformincludes a portal agentic system (e.g., illustrated in) configured to deliver key efficiencies by delegating the workflowassociated with the taskto the plurality of agents. In some embodiments, the portal agentic system is configured as one of the modalities of the agentic system. In some embodiments, the portal agentic system is configured as a user-friendly workflow-centric terminal (e.g., chatbot) for a user to make calls. In some embodiments, the workflow, in whole or in part, is pre-built to leverage built-in automated steps (e.g., an automated step to build a machine learning model via the AI platform, an automated step to access a database via the database platform, an automated step to acquire documents from the documentation platform, etc.). In some embodiments, the AI agentic portal associated with the agentic systemincludes APIs communicatively coupled (e.g., by wire and/or wireless) to the plurality of functional platforms. In some embodiments, the plurality of agentsand/or a subset of the plurality of agentsare dynamically spawned (e.g., created) using a collection of resources received from and/or stored in the plurality of functional platforms(e.g., the user platform, the AI platform, the database platform, the cloud platform, the computing platform, the device platform, the documentation platform, and/or the UI platform). In response to generating and transmitting output data to a user, the plurality of agentsand/or the subset of the plurality of agentsare automatically terminated, thereby releasing the collection of resources utilized during spawning. Stated another way, the spawned plurality of agentsand/or subset of the plurality of agentsare ephemeral. The agentic systemspawns respective agents and executes the taskas a process in memory. Once the taskis completed and the resultis provided to the user, the respective agents are shut down and terminated to release associated computational resources.

102 100 102 102 150 7 8 FIGS.-E In some embodiments, the agentic systemof the agentic orchestration platformincludes a web user interface (WebUI) agentic system (e.g., illustrated in) configured to provide an efficient user interface for user queries. In some embodiments, the WebUI agentic system is configured as one of the modalities of the agentic system. In some embodiments, the WebUI agentic system is a self-service and interactive platform that enables users to engage in real-time web-based conversations and chats with the agentic system. For example, the WebUI agentic system provides a seamless, user-friendly interface for sending user queries (e.g., searching incident logs, summarizing historical incidents, summarizing standard operating procedures), initiating workflows associated with the user queries, receiving responses (e.g., output data), and interacting with the plurality of agentswithin a web-based environment.

102 100 150 130 102 102 150 130 134 102 150 106 118 130 132 102 134 106 130 134 150 134 140 In some embodiments, the agentic systemof the agentic orchestration platformincludes an LLM-based agentic system (e.g., an LLM-based framework) configured to enable the plurality of agentsto autonomously and adaptively analyze the taskby integrating reasoning, learning, and decision-making capabilities. In some embodiments, the LLM-based agentic system is configured as one of the modalities of the agentic system. In some embodiments, the agentic systemperforms autonomous reasoning (e.g., using LLMs). For example, the plurality of agents, without supervision, analyze the task, perform internal reasoning, and determine optimal actions, thereby reducing the need or the supervision. In some embodiments, the agentic systemaugments human workforce (e.g., using LLMs). For example, the plurality of agentsassist human teams (e.g., users of the user platform) by leveraging historical data (e.g., received via the database platform and/or the documentation platform) related to present incidents (e.g., the task), insights and recommendations (e.g., the result) to enhance human decision-making and efficiency. In some embodiments, the agentic systemimplements LLMs to receive the supervision(e.g., from a user via the user platform) and analyzes the taskcorresponding to the supervision. For example, the plurality of agentsreceive the supervisionprior to executing an action (e.g., a respective step associated with the workflow) that alters a current state, thereby ensuring that critical decisions are reviewed and approved by user(s).

2 FIG. 1 FIG. 200 102 200 202 204 206 210 208 208 is a block diagram illustrating a computer systemthat supports the agentic system(e.g., in reference to), in accordance with some embodiments. The computer systemincludes one or more central processing units (CPU(s), i.e., processors or cores), one or more communication interfaces, one or more network interfaces, memory, and one or more communication busesfor interconnecting these components. The communication busesoptionally include circuitry (e.g., a chipset) that interconnects and controls communications between system components.

206 104 106 108 110 112 114 116 118 120 206 207 104 207 206 In some embodiments, the one or more network interfacesinclude wireless and/or wired interfaces for receiving data from and/or transmitting data to the plurality of functional platforms(e.g., the user platform, the AI platform, the database platform, the cloud platform, the computing platform, the device platform, the documentation platform, and/or the UI platform) and/or other devices or systems. In some embodiments, data communications are carried out using any of a variety of custom or standard wireless protocols (e.g., NFC, RFID, IEEE 802.15.4, Wi-Fi, ZigBee, 6LoWPAN, Thread, Z-Wave, Bluetooth, ISA100.11a, WirelessHART, MiWi, etc.). Furthermore, in some embodiments, data communications are carried out using any of a variety of custom or standard wired protocols (e.g., USB, Firewire, Ethernet, etc.). For example, the one or more network interfacesinclude a wireless interfacefor enabling wireless data communications with the plurality of functional platformsand/or or other wireless (e.g., Bluetooth-compatible) devices (e.g., for displaying data, storing data, processing data, etc.). Furthermore, in some embodiments, the wireless interface(or a different communications interface of the one or more network interfaces) enables data communications with other WLAN-compatible components (e.g., devices, servers, clouds, and/or other types) for displaying data, storing data, processing data, or other purposes related to IT operations and agentic orchestration.

210 210 202 210 210 210 210 220 an operating systemthat includes procedures for handling various basic system services and for performing hardware-dependent tasks; 222 102 104 150 communication module(s)for transmitting data (e.g., between the agentic systemand the plurality of functional platforms, between the plurality of agents), handling protocols (e.g., authentication/encryption), detecting error, and/or other functions; 224 102 104 206 network module(s)for connecting the agentic systemto the plurality of functional platformsand/or other devices or systems, via the one or more network interfaces(wired or wireless); 226 104 226 104 228 106 a user platform sub-module(e.g., for communicating data with the user platform); 230 108 an AI platform sub-module(e.g., for communicating data with the AI platform); 232 110 a database platform sub-module(e.g., for communicating data with the database platform); 234 112 a cloud platform(e.g., for communicating data with the cloud platform); 236 114 a computing platform sub-module(e.g., for communicating data with the computing platform); 238 116 a device platform sub-module(e.g., for communicating data with the device platform); 240 118 a documentation platform sub-module(e.g., for communicating data with the documentation platform); 242 120 a UI platform sub-module(e.g., for communicating data with the UI platform); a functional platform moduleconfigured to communicate data with the plurality of functional platforms. In some embodiments, the functional platform modulealso includes the following sub-modules (or sets of instructions) associated with the plurality of functional platforms, or a subset or superset thereof: 244 102 an embedded agentic module(e.g., configured to drive the embedded agentic system of the agentic system); 246 102 a portal agentic module(e.g., configured to drive the portal agentic system of the agentic system); 248 102 a WebUI agentic module(e.g., configured to drive the WebUI agentic system of the agentic system); 250 102 an LLM agentic module(e.g., configured to drive the LLM-based agentic system of the agentic system); 252 a user interface modulethat receives commands and/or inputs from a user via a user interface (e.g., from an input device) and provides outputs for display on the user interface (e.g., to an output device); 254 a web browser applicationfor accessing, viewing, and interacting with web sites; and 256 other applications, such as applications for word processing, calendaring, mapping, weather, time keeping, virtual digital assistant, presenting, number crunching (spreadsheets), drawing, instant messaging, e-mail, telephony, video conferencing, photo management, video management, and/or other purposes. Memoryincludes high-speed random-access memory, such as DRAM, SRAM, DDR RAM, or other random-access solid-state memory devices; and may include non-volatile memory, such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid-state storage devices. Memorymay optionally include one or more storage devices remotely located from the CPU(s). Memory, or alternately, the non-volatile memory solid-state storage devices within memory, includes a non-transitory computer-readable storage medium. In some embodiments, memoryor the non-transitory computer-readable storage medium of memorystores the following programs, modules, and data structures, or a subset or superset thereof:

210 210 210 Each of the above identified modules stored in memorycorresponds to a set of instructions for performing a function described herein. The above identified modules or programs (i.e., sets of instructions) need not be implemented as separate software programs, procedures, or modules, and thus various subsets of these modules may be combined or otherwise re-arranged in various embodiments. Likewise, although shown as stored in a single memory, the above-identified modules may be stored on physically separate memories and/or executed on physically separate (e.g., remote) devices. In some embodiments, memoryoptionally stores a subset or superset of the respective modules and data structures identified above. Furthermore, memoryoptionally stores additional modules and data structures not described above.

3 FIG. 1 FIG. 1 FIG. 1 FIG. 1 FIG. 300 300 102 100 300 102 102 102 330 306 106 350 1 140 140 342 342 1 342 102 140 350 2 352 352 1 342 342 352 102 140 352 332 102 334 134 332 350 1 102 334 350 2 332 332 102 332 332 102 332 306 106 116 m n illustrates an example agentic orchestration platform, in accordance with some embodiments. In particular, the example agentic orchestration platformimplements the agentic systemand presents a platform configuration corresponding to the agentic orchestration platform(e.g., in). In some embodiments, the example agentic orchestration platformis configured as the portal agentic system (e.g., one of the modalities of the agentic system). In some embodiments, the agentic systemis configured as an integrated multi-agent framework configured to reason, learn, execute tasks, and make decisions while communicating and collaborating internally (e.g., between agents) and externally (e.g., with humans/users) to solve tasks (e.g., critical and high-priority incidents, user requests, user queries). In some embodiments, the agentic systemgenerates, based on a user requestof a user(e.g., via the user platformin) and by a first agent-, a workflow(in). The workflowincludes a plurality of steps(e.g., step-to step-, where m is an integer greater than two). The agentic systemfurther generates, based on the workflowand by a second agent-, one or more on-demand agents(e.g., first on-demand agent-to n-th on-demand agent-, where n is an integer greater than one). Each of the plurality of stepsis assigned to (e.g., executed by) a respective on-demand agent of the one or more on-demand agents. The agentic systemfurther analyzes the workflowby the one or more on-demand agentsto generate output data. The agentic systemfurther receives user supervision(e.g., supervisionin) associated with the output databy the first agent-. The agentic systemfurther determines, based on the user supervisionand by the second agent-, whether the output datarequires updating. In accordance with a determination that the output datarequires updating, the agentic systemfurther updates the output datato form updated output data′. The agentic systemfurther displays the updated output datato the user(e.g., on a display device via the user platformand/or the device platform).

350 1 350 2 352 104 106 108 110 112 114 116 118 120 In some embodiments, each agent of the first agent-, the second agent-, and the one or more on-demand agentsis driven by a respective computational component from a plurality of computational components (e.g., data analytics, analytical models, machine-learning models, LLMs, plugins, other types of models, or a combination of various types). In some embodiments, the plurality of computational components are built using a combination of resources received from and/or stored in the plurality of functional platforms(e.g., the user platform, the AI platform, the database platform, the cloud platform, the computing platform, the device platform, the documentation platform, and/or the UI platform). In some embodiments, the plurality of computational components include at least one of the group consisting of (i) an analytical model (e.g., regression model, decision tree, clustering, etc.), (ii) an LLM (e.g., deep learning models, natural language processing, etc.), and (iii) a plugin (e.g., query plugin, automation plugin, chatbot plugin, knowledge base integration, etc.).

350 1 450 1 306 350 2 350 1 330 104 330 350 1 140 350 1 350 1 330 4 FIG. In some embodiments, the first agent-is an external agent (e.g., an externally-facing agent, such as agent “KING”-in) configured to communicate data with the userand the second agent-. In some embodiments, the first agent-is dynamically created (e.g., on an as-needed basis, on-demand) based on the user requestusing resources provided in the plurality of functional platforms. For example, when the user requestincludes a critical and high-priority incident, the first agent-is created on an as-needed basis to analyze the incident to generate the workflow. In some embodiments, the first agent-is hard-coded. For example, the first agent-is a hard-coded model (e.g., a script to generate workflow(s), an API to an LLM, an LLM plugin) independently built regardless of the type of the user request.

350 2 450 2 350 1 352 140 350 2 350 1 104 350 1 140 330 140 350 1 350 1 350 2 140 350 2 350 2 330 4 FIG. In some embodiments, the second agent-is an internal agent (e.g., internally-facing agent, such as agent “ANALYST”-in) configured to communicate data with the first agent-and supervise (e.g., coordinate) the one or more on-demand agentsbased on the workflow. In some embodiments, the second agent-is dynamically created (e.g., on an as-needed basis, on-demand) by the first agent-using resources provided in the plurality of functional platforms. For example, when the first agent-identifies the workflowfrom the user requestand determines that it is capable of processing the workflow(e.g., due to excessive computation resources required by the first agent-, a need for specific model(s) and/or data analytics that the first agent-does not support) creates the second agent-on an as-needed basis to process the workflow. In some embodiments, the second agent-is hard-coded. For example, the second agent-is a hard-coded model (e.g., a script to process workflow(s), an API to an LLM, an LLM plugin) independently built regardless of the type of the user request.

350 2 102 104 350 2 In some embodiments, the second agent-is in compliance with a remote procedure call (RPC) framework for external functions. In particular, the RPC framework allows the agentic systemto execute functions and/or procedures located on external systems/platforms (e.g., the plurality functional platforms) as if they were local. Moreover, the RPC framework provides libraries and protocols for creating communication channels, performing serialization, and handling errors. In some embodiments, the second agent-implements a gRPC Remote Procedure Call framework.

352 350 2 104 352 2 352 352 1 352 104 352 1 342 1 342 2 352 1 352 2 342 2 352 1 352 2 104 352 In some embodiments, the one or more on-demand agentsare dynamically created (e.g., on an as-needed basis, on-demand) by the second agent-using resources provided in the plurality of functional platforms. In some embodiments, a respective on-demand agent (e.g., the second on-demand agent-) of the one or more on-demand agentsis dynamically created by another respective on-demand agent (e.g., the first on-demand agent-) of the one or more on-demand agentsusing resources provided in the plurality of functional platforms. For example, when the first on-demand agent-identifies, based on the step-, that a subsequent step-exists and needs to be processed, the first on-demand agent-creates the second on-demand agent-to execute the step-. In some embodiments, a respective on-demand agent (e.g., the first on-demand agent-) is configured to create another respective on-demand agent (e.g., the second on-demand agent-) using resources provided in the plurality of functional platforms. In some embodiments, a subset of the one or more on-demand agentsare hard-coded.

330 130 330 130 350 1 320 306 350 1 350 1 140 332 132 306 1 FIG. 1 FIG. 1 FIG. In some embodiments, the user requestis a task (e.g., taskin, such as a request to resolve critical and high-priority incident, a request to access a database, a request to create a SOP based on a pool of SOPs). In some embodiments, the user requestis configured as a user query based on the task (e.g., taskin). The first agent-receives the user query (e.g., a natural language query, a data query) associated with the user requestfrom the user. The first agent-further identifies, based on the user query, a user intent (e.g., in forms of word embeddings). The first agent-further creates, based on the user intent, the workflow(e.g., by comparing word embeddings). In some embodiments, the output dataare included in a result (e.g., resultin, such as recommendations/solutions to a critical and high-priority incident, summaries of historical incidents, scripts for generating SOPs) for the user.

140 330 332 332 342 306 352 342 352 1 352 1 352 342 1 342 2 352 1 In some embodiments, the workflowdefines, based the user request, a process to generate the output dataand the updated output data′. In particular, the plurality of stepsdefine specific actions/activities for generating a target output for the user, which are executed by the one or more on-demand agents. In some embodiments, each of the plurality of stepsis assigned to (e.g., executed by) a respective on-demand agent (e.g., the first on-demand agent-) that is distinct from remaining on-demand agent(s) of the respective on-demand agent (e.g., the first on-demand agent-). Stated another way, each of the one or more on-demand agentsis distinct from each other. In some embodiments, one or more steps (e.g., the step-and the step-) are assigned to (e.g., executed by) the same on-demand agent (e.g., the first on-demand agent-).

140 102 140 350 1 330 350 1 342 350 1 342 In some embodiments, the workflowincludes a schema. In particular, the schema is easily parsed and processed by the agentic system, thereby providing various advantages such as consistency, automation, scalability, adaptability, visualization and more. In some embodiments, the schema is in form of a JavaScript Object Notation (JSON) (e.g., the workflowis a JSON file). In some embodiments, the first agent-parses the user request(e.g., breaking a text query into words, phrases, or symbols) to generate an abstract syntax tree (AST). The first agent-further analyzes the AST to identify the plurality of steps. The first agent-further generates the schema based on the plurality of steps.

342 342 1 342 2 342 330 342 350 2 350 2 332 332 m In some embodiments, each of the plurality of steps(e.g., the steps-,-, . . .-) includes a respective task message (e.g., in format of a Gherkin statement, a schema, or other type) identifying a respective task. In some embodiments, a respective task is configured as a sub-task of the user requestand defines a corresponding step to be performed. In some embodiments, for each of the plurality of steps, the second agent-analyzes the respective task message, and identifies, based on the analyzed respective task message, the respective on-demand agent. The respective on-demand agent processes the respective task to generate respective data. In particular, the respective data generated by the respective on-demand agent is used by the second agent-to generate the output data(e.g., the respective data are part of the output data).

350 1 350 2 352 362 1 352 1 456 362 1 362 1 352 2 458 362 2 352 2 342 2 342 1 362 1 362 2 352 2 458 362 2 362 2 352 3 460 362 2 352 3 342 3 342 2 362 2 4 FIG. 4 FIG. 4 FIG. 4 FIG. In some embodiments, the agents (e.g., the first agent-, the second agent-, and/or the one or more on-demand agents) communicate internally through communication messages (e.g., in format of a schema). In some embodiments, respective data generated by a respective on-demand agent include a respective communication message (e.g., in format of a schema) for another respective on-demand agent that processes another respective task subsequent to the respective task. Stated another way, the respective communication message is configured as an instruction for the other on-demand agent to follow when processing the other respective task subsequent to the respective task. For example, the respective data-(e.g., Python scripts) generated by the first on-demand agent-(e.g., agent “DEVELOPER”in) include a respective communication message that has an indication that the respective data-needs to be executed and/or other information (e.g., code language, code length, process priority, etc.) associated with the respective data-. When the second on-demand agent-(e.g., agent “EXECUTOR”in) receives the respective data-, the second on-demand agent-processes the respective task of the step-, which is subsequent to the respective task of the step-, in accordance with the respective communication message of the respective data-. In another example, the respective data-(e.g., executed Python scripts) generated by the second on-demand agent-(e.g., agent “EXECUTOR”in) include a respective communication message that have an indication that the respective data-needs to be reviewed and/or other information (e.g., code language, number of the reviewed Python scripts, target length of a consolidated script, process priority, etc.) associated with the respective data-. When the third on-demand agent-(e.g., agent “REVIEWER”in) receives the respective data-, the third on-demand agent-processes the respective task of the step-, which is subsequent to the respective task of the step-, in accordance with the respective communication message of the respective data-.

102 350 1 102 334 332 334 332 332 350 1 102 332 306 336 334 332 350 1 336 334 332 106 120 306 332 334 332 332 102 332 332 334 458 456 102 334 4 FIG. 4 FIG. In some embodiments, the agentic systemreceives supervision (e.g., user supervision, user input, user interception) to make more effective decisions and ensure safety and accuracy. In some embodiments, the first agent-of the agentic systemreceives the user supervisionassociated with the output data. In particular, the user supervisionis configured as a user input or a user interception that provides feedback (e.g., error detection, performance metrics, real-time monitoring, operational feedback, auditing/compliance check, user satisfaction) to the output dataand is used to determine whether the output datarequires updating. In some embodiments, the first agent-of the agentic systemdisplays the output datato the user, and receives a user input(e.g., a user query, a textual input, etc.) including the user supervisionthat identifies a correctness of the output data. Stated another way, the first agent-receives the user inputincluding the user supervisionafter the output datais shown (e.g., displayed via the user platformand/or the UI platform) to the user. In some embodiments, the correctness of the output datais determined by a plurality of factors, including but not limited to precision, consistency, error rate, relevance, data integrity, and robustness. In some embodiments, the user supervisionincludes a user input to accept or reject the output data. When the user input rejects the output data, the agentic systemupdates the output datato form updated output data′ (e.g., a new set of data) for receiving another user supervision. In some embodiments, the user supervisionincludes a user approval (e.g., authorization) and a user rejection. For example, before an agent (e.g., the agent “EXECUTOR”in) executes a code script created by another agent (e.g., agent “DEVELOPER”in), the agentic systemreceives a user authorization to proceed with executing the code script by the other agent. In some embodiments, the user supervisionincludes a two-fold supervision: (i) a user reviews and provides clarifications and (ii) a user authorizes an execution for an agent to execute a respective task.

350 2 336 334 350 1 334 336 332 332 332 334 332 352 332 350 2 334 334 332 102 334 334 332 350 2 342 1 456 334 342 1 334 362 1 332 332 334 332 350 2 342 3 460 334 342 3 334 362 3 332 332 4 FIG. 4 FIG. In some embodiments, the second agent-receives the user inputhaving the user supervisionvia the first agent-and determines, based on the user supervision, the user input, whether the output datarequires updating. In some embodiments, the determination of whether the output datarequires updating corresponds to the correctness of the output dataidentified by the user supervision. In some embodiments, the determination of whether the output datarequires updating includes determining a respective on-demand agent of the one or more on-demand agentsthat is responsible for updating the output data. In particular, the second agent-identifies a respective on-demand agent associated with the user supervision. The respective on-demand agent determines, based on the user supervision, whether the output datarequires updating. Stated another way, in some embodiments, the agentic systemis configured to identify which agent (e.g., on-demand agent) is responsible for analyzing the user supervision. For example, when the user supervisionidentifies that the output data(e.g., a consolidated script to generate a unified SOP) was not correctly generated due to the use of incorrect SOPs and the second agent-identifies that the on-demand agent-(e.g., agent “DEVELOPER”in) is associated with the user supervision, the on-demand agent-determines, based on the user supervision, that the respective data-requires updating because wrong SOPs were used. As such, the output datais updated to form the updated output data′. In another example, when the user supervisionidentifies that the output data(e.g., a unified SOP) contains grammatical errors and the second agent-identifies that the on-demand agent-(e.g., agent “REVIEWER”in) is associated with the user supervision, the on-demand agent-determines, based on the user supervision, that the respective data-requires updating because the grammatical errors need corrections. As such, the output datais updated to form the updated output data′.

334 336 334 350 2 334 332 334 306 332 334 306 332 In some embodiments, in response to receiving the user supervision(or the user inputincluding the user supervision), the second agent-determines, based on the user supervision, whether the output datarequires updating. Stated another way, in some embodiments, receiving the user supervisionfrom the useris a prerequisite for updating the output data. In some embodiments, receiving the user supervisionfrom the useris optional. In this situation, no update to the output datais required.

334 352 334 350 2 334 350 2 334 332 350 2 342 1 456 334 350 2 342 1 342 1 342 1 342 1 362 1 332 332 4 FIG. In some embodiments, the user supervisioninitiates an update to a respective on-demand agent of the one or more on-demand agents. Stated another way, a respective on-demand agent is updated based on the user supervision. In particular, when the second agent-identifies that a respective on-demand agent is associated with the user supervision, the second agent-updates the respective on-demand agent. For example, when the user supervisionindicates that the output datawere not properly generated due to the use of incorrect model(s) and the second agent-identifies that the on-demand agent-(e.g., agent “DEVELOPER”in) is associated with the user supervision, the second agent-is configured to update the on-demand agent-(e.g., rebuilding the on-demand agent-using updated model(s), tuning existing model(s) used by the on-demand agent-). As such, the on-demand agent-is updated, thereby updating the respective data-and the output datato form the updated output data′.

102 334 332 102 350 1 350 2 332 338 338 338 102 330 In some embodiments, the agentic systemimplements an iterative process to receive the user supervisionfor updating the output data. In particular, the agentic systemiteratively receives respective user supervision associated with respective output data by the first agent-, determines, based on the respective user supervision and by the second agent-, whether the respective output data requires updating, and in accordance with a determination that the respective output data requires updating, updating the respective output data. Stated another way, in some embodiments, updating the output datarequires one or more feedback loops, and each of the one or more feedback loopscorresponds to respective output data and respective user supervision. The iterative process, driven by the one or more feedback loops, enables the agentic systemto operate under supervision, ensuing decision-making and adaptability in complex, dynamic environments associated with the user request.

4 FIG. 400 102 400 300 400 102 400 106 116 120 400 306 illustrates an example UIbuilt for the agentic system, in accordance with some embodiments. In some embodiments, the example UIfunctions as a user interface (e.g., a chatbot) for the example agentic orchestration platform. In some embodiments, the example UIis configured as a user interface for the portal agentic system (e.g., one of the modalities of the agentic system). In some embodiments, the example UIis part of the user platform, the device platform, and/or the UI platform. In some embodiments, the example UIis configured to display user request(s), user supervision, and output data to the user.

4 FIG. 400 402 404 402 306 450 1 404 450 1 450 2 452 454 456 458 460 404 400 306 450 1 450 2 350 1 350 2 456 458 460 352 As shown in, the example UIincludes a first paneland a second panel. In some embodiments, the first paneldisplays interactions between the userand an agent “KING”-. The second paneldisplays interactions between agents including the agent “KING”-, an agent “ANALYST”-, an agent “PARSER”, an agent “SUMMARIZER”, an agent “DEVELOPER”, an agent “EXECUTOR”, an agent “REVIEWER”. In some embodiments, the second panelof the example UIis hidden and not shown to the user. In some embodiments, the agent “KING”-and the agent “ANALYST”-are configured as the first agent-and the second agent-, respectively. In some embodiments, the agent “DEVELOPER”, the agent “EXECUTOR”, and the agent “REVIEWER”are configured as on-demand agents (e.g., the one or more on-demand agents).

400 102 430 306 450 1 140 140 442 442 1 442 2 442 3 102 140 450 2 456 458 460 442 456 458 460 442 1 442 2 442 3 456 458 460 102 140 456 458 460 432 In some embodiments, as shown in the example UI, the agentic systemgenerates, based on a user request(e.g., “create a Python script that generalizes the standard of procedure”) of the userand by the agent “KING”-, a workflow. The workflowincludes a plurality of steps(e.g., steps-,-, and-). The agentic systemfurther generates, based on the workflowand by the agent “ANALYST”-, the agents “DEVELOPER”, “EXECUTOR”, and “REVIEWER”. Each of the plurality of stepsis assigned to (e.g., executed by) a respective agent of the agents “DEVELOPER”, “EXECUTOR”, and “REVIEWER”. For example, the steps-,-, and-are assigned to (e.g., executed by) the agents “DEVELOPER”, “EXECUTOR”, and “REVIEWER”, respectively. The agentic systemfurther analyzes the workflowby the agents “DEVELOPER”, “EXECUTOR”, and “REVIEWER”to generate output data(e.g., a Python script).

442 442 1 442 2 442 3 442 450 2 450 2 432 450 2 442 1 442 1 450 2 456 442 1 462 1 432 450 2 442 2 442 2 450 2 458 442 2 462 2 432 450 2 442 3 442 3 450 2 460 442 2 462 2 432 In some embodiments, each of the plurality of stepsincludes a respective task message identifying a respective task. For example, the step-includes a first respective task message “develop a script,” the step-includes a second respective task message “execute a script,” and the step-includes a third respective task message “review a script.” In some embodiments, for each of the plurality of steps, the agent “ANALYST”-analyzes the respective task message, and identifies, based on the analyzed respective task message, the respective agent. The respective agent processes the respective task to generate respective data. In particular, the respective data generated by the respective agent is used by the agent “ANALYST”-to generate the output data(e.g., a Python script). For example, when the agent “ANALYST”-analyzes the respective message “develop a script” of the step-and determines that the step-requires developing a Python script based on a series of SOPs, the agent “ANALYST”-identifies the agent “DEVELOPER”to process the respective task of the step-(e.g., creating a Python script based on the series of SOPs by consolidating the series of SOPs into a single script) for generating respective data-as part of the output data. In another example, when the agent “ANALYST”-analyzes the respective message “execute the script” of the step-and determines that the step-requires executing the Python script, the agent “ANALYST”-identifies the agent “EXECUTOR”to process the respective task of the step-(e.g., executing the Python script) for generating respective data-(e.g., a unified SOP) as part of the output data. In yet another example, when the agent “ANALYST”-analyzes the respective message “review the script” of the step-and determines that the step-requires reviewing the Python script and/or the unified SOP generated by the Python script, the agent “ANALYST”-identifies the agent “REVIEWER”to process the respective task of the step-(e.g., detecting error(s) and validating the Python script) for generating respective data-(e.g., a reviewed Python script with necessary corrections) as part of the output data.

102 452 454 452 454 450 1 452 330 452 342 452 462 342 454 464 462 450 1 464 140 306 400 In some embodiments, the agentic systemgenerates an agent “PARSER”and an agent “SUMMARIZER”. In some embodiments, the agent “PARSER”and the agent “SUMMARIZER”are included in the agent “KING”-. In some embodiments, the agent “PARSER”parses the user request(e.g., breaking a text query into words, phrases, or symbols) to generate an abstract syntax tree (AST). The agent “PARSER”further analyzes the AST to identify the plurality of steps. The agent “PARSER”further generates a schemabased on the plurality of steps. In some embodiments, agent “SUMMARIZER”generates a summarybased on the schema. In some embodiments, the agent “KING”-displays the summary(e.g., the workflow) to the uservia the example UI.

5 FIG.A 5 FIG.B 500 102 510 102 500 510 502 512 530 502 512 140 530 130 330 500 510 102 502 512 510 102 illustrates an example incident management frameworkthat does not implement the agentic system, andillustrates another example incident management frameworkthat implements the agentic system, in accordance with some embodiments. The example incident management frameworksandinclude a first pipelineand a second pipeline, respectively, for resolving an incident(e.g., a critical and high-priority incident). In some embodiments, each of the first pipelineand the second pipelineis part of the workflowand identifies the steps. In some embodiments, the incidentis included in the taskand/or the user request. Compared with the example incident management framework, the example incident management frameworkis AI-augmented and built based on the agentic system. Stated another way, the first pipelineis executed only by humans, and the second pipelineis executed by human(s) and agents. In some embodiments, the example incident management frameworkis operated based on the portal agentic system (e.g., one of the modalities of the agentic system).

5 FIG.A 502 542 1 542 2 542 3 542 4 542 5 530 542 1 542 2 330 542 3 542 4 542 5 In some embodiments, as shown in, the first pipelineincludes six steps: step 0, step 1 (e.g., step-), step 2 (e.g., step-), step 3 (e.g., step-), step 4 (e.g., step-), and step 5 (e.g., step-). The step 0 is configured to create the incident, which is executed by one user (e.g., a helpdesk supporter). The step 1 (e.g., step-) is configured to convene an incident bridge, which is executed by approximately one user (e.g., an incident manager). The step 2 (e.g., step-) is configured to investigate issues corresponding to the user request, which is executed by approximately seven users (e.g., subject matter experts (SMEs)). The step 3 (e.g., step-) is configured to develop (e.g., generate) mitigation plan(s) and documentation(s) (e.g., SOP(s)), which is executed by approximately three users (e.g., SMEs). The step 4 (e.g., step-) is configured to execute the generated mitigation plan(s) and documentation(s) and make corrective action(s), which is executed by approximately one user (e.g., SME). The step 5 (e.g., step-) is configured to review (e.g., validate) the generated mitigation plan(s) and documentation(s) and restore service(s), which is executed by approximately three users (e.g., SMEs).

502 500 530 As discussed above, the first pipelineis executed only by humans (e.g., users such as helpdesk supporter(s), incident manager(s), and SMEs). TABLE I illustrates approximately durations associated with each step in the example incident management framework. A total duration required to resolve the incidentand restore service(s) is approximately 5 hours 15 mins.

TABLE I Number Steps Role Approx. Duration 0 Incident Creation Helpdesk Supporter 15 mins (e.g., one (1) user) 1 Incident Bridge Convened Incident Manager 15 mins (e.g., step 542-1) (e.g., one (1) user) 2 Issue Investigation Subject Matter Experts 2 hours (e.g., step 542-2) (e.g., seven (7) users) 3 Mitigation Plan & Subject Matter Experts 45 mins Documentation (e.g., three (3) users) (e.g., step 542-3) 4 Corrective Action & Execution Subject Matter Expert 1 hour 30 mins (e.g., step 542-4) (e.g., one (1) user) 5 Validation & Service Restored Subject Matter Experts 30 mins (e.g., step 542-5) (e.g., three (3) users) Total Duration from Incident to Restoration 5 hours 15 mins

5 FIG.B 1 FIG. 512 542 1 542 2 542 3 542 4 542 5 502 502 512 102 102 552 552 1 552 2 550 3 552 4 552 5 542 1 542 5 552 512 552 1 542 1 552 5 542 5 542 1 542 3 550 1 552 1 552 2 552 2 542 1 552 1 552 1 552 352 150 In some embodiments, as shown in, the second pipelinealso includes six steps: step 0, step 1 (e.g., step-), step 2 (e.g., step-), step 3 (e.g., step-), step 4 (e.g., step-), and step 5 (e.g., step-), similar to those steps included in the first pipeline. Different from the first pipeline, a majority of the steps of the second pipelineare executed by agents of the agentic system. In particular, the agentic systemincludes a plurality of on-call agents(e.g., first on-call agent-, second on-call agent-, third on-call agent-, fourth on-call agent-, and fifth on-call agent-) for executing the steps-to-. Each of the plurality of on-call agentsexecutes a corresponding step in accordance with the second pipeline. For example, the first on-call agent-executes the step-to convene an incident bridge. In another example, the fifth on-call agent-executes the step-to review (e.g., validate) the generated mitigation plan(s) and documentation(s) and restore service(s). In some embodiments, two or more respective steps (e.g., the steps-and-) are assigned to the same on-call agent (e.g., the first agent-), such that the first on-agent-replaces the second on-agent-and the second on-agent-is no longer needed. In some embodiments, a respective step (e.g., steps-) is assigned to one or more on-call agents. For example, the first on-call agent-includes two on-call agents for executing the step-. In some embodiments, the plurality of on-call agentsand the one or more on-demand agentsare exchangeable, and they are part of the plurality of agents(in).

512 552 1 552 5 510 530 500 As discussed above, the second pipelineis executed by human(s) and five on-call agents-to-. TABLE II illustrates approximately durations associated with each step in the example incident management framework. A total duration required to resolve the incidentand restore service(s) is approximately 1 hour 50 mins, which is significantly less than the approximate duration of 5 hours 15 mins required by the example incident management framework.

TABLE II Number Steps Role Approx. Duration 0 Incident Creation A human (e.g., 15 mins Helpdesk Supporter) (e.g., one (1) user) 1 Incident Bridge Convened Human and an agent 15 mins (e.g., step 542-1) (e.g., one (1) user) 2 Issue Investigation An agent 30 mins (e.g., step 542-2) (e.g., zero (0) user) 3 Mitigation Plan & An agent 15 mins Documentation (e.g., zero (0) user) (e.g., step 542-3) 4 Corrective Action & Execution An agent 30 mins (e.g., step 542-4) (e.g., zero (0) user) 5 Validation & Service Restored A human and an agent 15 mins (e.g., step 542-5) (e.g., one (1) user) Total Duration from Incident to Restoration 1 hour 50 mins

510 300 542 3 552 3 532 532 506 102 534 1 532 552 4 532 552 4 532 534 542 5 552 5 534 102 534 2 506 534 102 552 5 534 506 534 2 3 FIG. In some embodiments, the example incident management frameworkoperates under supervision (e.g., user supervision, user input, user interception, etc.), similar to the example agentic orchestration platform(in). For example, in the step 3 (e.g., step-), the third on-call agent-develops (e.g., generates) mitigation plan(s) and documentation(s) (e.g., SOP(s)) as part of output data. The output datais displayed to a user (e.g., the userand/or other human(s)). The agentic systemreceives first user supervision-(e.g., an agent-human interaction) for determining whether the output datarequires updating. In accordance with a determination by the fourth on-call agent-that the output datarequires updating, fourth on-call agent-updates the output datato generate updated output data. In another example, in the step 5 (e.g., step-), the fifth on-call agent-reviews (e.g., validates) the updated output data(e.g., updated mitigation plan(s) and documentation(s)) and restore service(s). The agentic systemreceives second user supervision-(e.g., an instruction from the userand/or other human(s) indicating how to display the updated output data). The agentic systemdisplays (e.g., by the fifth on-call agent-) the updated output datato the userin accordance with the second user supervision-.

552 104 102 530 102 552 1 542 1 552 1 542 2 552 1 552 2 542 2 552 1 530 In some embodiments, the plurality of on-call agentsare dynamically created (e.g., on an as-needed basis, on-demand) using resources provided in the plurality of functional platforms. For example, when the agentic systemidentifies a need to convene an incident bridge based on message(s) carried by the incident, the agentic systemdynamically creates the first on-call agent-to execute the step-. In another example, when the first on-call agent-identifies a need to execute a subsequent step (e.g., the step-) that requires an agent to search for issue from knowledgebase based on incident parameters, the first on-call agent-dynamically creates the second on-call agent-to execute the step-. In some embodiments, the first on-call agent-is hard-coded, because it would be certain that at least one on-call agent is needed to resolve the incident.

552 1 552 552 2 552 5 552 552 1 506 530 512 140 530 530 532 534 506 552 1 552 2 552 5 104 108 112 114 1 FIG. In some embodiments, a respective on-call agent (e.g., the first on-call agent-) of the plurality of on-call agentsis a central on-call agent and remaining agents (e.g., the second to fifth on-call agents-to-) of the plurality of on-call agentsare non-central on-call agents. For example, the central on-call agent (e.g., agent-) is configured to communicate externally with the userto receive the incident, generate the second pipeline(e.g., the workflow) based on the incident, coordinate (e.g., orchestrate) the non-central on-call agents to analyze the incidentto generate data (e.g., the output dataand/or the updated output data), and send the data to the user. In another example, the central on-call agent (e.g., agents-) dynamically creates the non-central on-call agents (e.g., agents-to-) using a combination of resources provided in the plurality of functional platforms(e.g., creating a respective on-call agent as needed using resources provided by the AI platform, the cloud platform, and the computing platformin).

6 FIG. 1 FIG. 600 102 600 102 104 102 102 102 600 102 600 510 102 illustrates an example incident management frameworkthat implements the agentic system, in accordance with some embodiments. In particular, the example incident management frameworkfacilitates dynamically spawning and automatically terminating agents (e.g., on-call agents), thereby enhancing operational efficiency, responsiveness, and sustainability of the agentic system. For example, the capability of dynamically spawning and automatically terminating agents ensures that computational resources (e.g., resource of functional platformsin) are allocated only when needed, preventing idle agents (e.g., agents who have accomplished assigned tasks) from consuming memory, CPUs, or storages. In another example, this dynamic configuration enables the agentic systemto scale efficiently based on real-time incident management demands. During peak loads, the agentic systemis configured to spawn additional agents to maintain optimal performance, while during low loads, the agentic systemis configured to terminate idle agents (e.g., agents who have accomplished assigned tasks) to conserve computational resources. In yet another example, automatically terminating agents allows for minimization of superfluous computational resource consumption particularly in cloud-based environments. In some embodiments, the example incident management frameworkis operated based on the portal agentic system (e.g., one of the modalities of the agentic system). In some embodiments, the example incident management frameworkis similar to the example incident management framework, each of which is AI-augmented and built based on the agentic system. In some embodiments, on-call agents and on-demand agents are exchangeable.

6 FIG. 1 FIG. 4 FIG. 102 606 630 631 630 102 630 631 630 102 630 631 102 630 650 660 662 660 102 606 660 102 102 604 104 652 662 102 108 112 114 104 102 652 632 652 630 652 102 632 606 632 606 102 102 652 604 652 630 631 631 652 552 1 552 5 604 652 606 652 652 450 1 450 2 652 604 652 652 652 652 632 606 In some embodiments, as shown in, the agentic systemreceives, from a user(e.g., a human who creates an incident based on an internal/external customer's input), an incidentdefining a target issueto be addressed. For example, the incidentincludes a critical and high-priority incident that requires an immediate attention from the agentic system. In this circumstance, the incidentdefines the target issueas the resolutions of errors (e.g., data errors, access errors, configuration errors, etc.) or failures (e.g., network failures, API failures, cloud service outages, domain secure session setup failures, etc.). In another example, the incidentincludes an operation that requires processing (e.g., model training, data searching, etc.) via the agentic system. In this circumstance, the incidentdefines the target issueas the execution of the operation. The agentic systemfurther convenes in real-time, based on the incidentand by a coordinating agent, a callthat defines a collaboration. For example, the callis convened without an intentionally introduced lag by the agentic systemor the user. In another example, the callis convened within a time frame that accounts for the processing time of the agentic system(e.g., a few seconds to under one minute). The agentic systemfurther dynamically spawns (e.g., creates on an as-needed basis), using computational resources(e.g., resource of functional platformsin), one or more on-call agentscorresponding to the collaboration. For example, the agentic systemdynamically spawns a respective on-call agent as needed using computational resources provided by the AI platform, the cloud platform, and the computing platformof the functional platforms. The agentic systemfurther generates, by the one or more on-call agents, output data. For example, the one or more on-call agentscreate an incident resolution report and/or a system log corresponding to the incident. In another example, the one or more on-call agentscreate an operational SOP as a recommendation for further prevention and resolution procedure. The agentic systemfurther transmits the output datato the user. For example, the output datais displayed to the uservia a graphical UI (e.g., a UI included in the portal agentic system of the agentic system). The agentic systemfurther automatically terminates the one or more on-call agentsby releasing the computational resources. For example, in a scenario where the one or more on-call agentsare spawned to diagnose the incidentthat defines the target issuerelevant to a system outage, when the target issueis resolved and a system log is recorded, the one or more on-call agents(e.g., the first to fifth on-call agents-to-) are terminated, such that the computational resources(e.g., CPUs, memory, network bandwidths, etc.) allocated to the one or more on-call agentsare freed up and assigned to other incident(s). In another example, in a scenario where a chatbot instance (e.g., a chatbot illustrated in) is created for inquiries, when interactions between the userand the one or more on-call agentsend, the one or more on-call agents(e.g., agent “KING”-, agent “ANALYST”-, etc.) or a subset of the one or more on-call agentsare terminated, such that the computational resources(e.g., server memory, processing power, virtual machines, etc.) allocated to the one or more on-call agentsare deallocated and freed up. In yet another example, in a scenario where machine learning models for resolving incidents are trained using the one or more on-call agentsacross graphics processing units (GPUs), when the training is completed, the one or more on-call agentsthat are used during the training are terminated, such that GPU memory and associated processing power are freed up and reallocated to other operation(s). In some embodiments, automatically terminating the one or more on-call agents(e.g., in the scenarios discussed above) corresponds to specific timing criteria. For example, the termination may occur after a predetermined period has elapsed subsequent to transmitting the output datato the user(e.g., further details to be discussed below). Alternatively, the termination may take place within a predetermined period and automatically cease after the predetermined period has elapsed (e.g., further details to be discussed below).

660 662 662 631 630 662 630 662 650 630 660 652 662 650 630 606 650 630 650 660 662 650 630 650 600 650 650 630 604 652 102 650 652 650 604 102 652 In some embodiments, the callincludes an incident bridge that defines the collaboration. The incident bridge is a communication channel for incident resolution. For example, the incident bridge facilitates a real-time coordination among humans and agents for efficient troubleshooting, decision-making, and task delegation. Specifically, the collaborationis established via the incident bridge to provide seamless information exchange, role assignments, and collective problem-solving to address the target issueof the incident. In some embodiments, the collaborationis a structured and coordinated efforts that identify how to diagnose, manage, and resolve the incidentefficiently. For example, the collaborationincludes real-time communication (e.g., between humans and agents, etc.), task coordination (e.g., specific actions, patch deployment, rollback procedures, methods of assigning agents on an as-needed basis, etc.), and workflow (e.g., incident resolution workflows, response procedures, predefined escalation approaches, protocols, etc.). In some embodiments, the coordinating agentis configured to interpret the incidentinto the calland coordinate agents (e.g., the one or more on-call agents) based on the collaboration. In one example, the coordinating agentreceives the incident(e.g., a natural language query, a data query) from the user. The coordinating agentfurther identifies, based on the incident, an intent (e.g., in forms of word embeddings). The coordinating agentfurther creates, based on the intent, the callincluding the collaboration. In another example, the coordinating agentmanages and orchestrates the resolution of the incidentvia the incident bridge (e.g., the coordinating agentacts as a central orchestrator within the example incident management framework). One primary role of the coordinating agentis to ensure efficient communication, task delegation, and resource allocation among humans and agents. In some embodiments, the coordinating agentmonitors the status of the incidentand manages the computational resourcesfor dynamically spawning and/or automatically terminating the one or more on-call agentson an as-needed basis to balance load and efficiency of the agentic system. For example, the coordinating agentis configured to allocate more computational resources (e.g., CPUs, memory, storages, and network bandwidths) to the one or more on-call agents. In another example, the coordinating agentis configured to dynamically balance and adjust the distribution of the computational resourcesbased on real-time load and system efficiency of the agentic system, thereby preventing performance bottlenecks in computing nodes for the one or more on-call agents.

630 102 650 630 102 650 102 604 630 102 650 630 650 650 650 630 650 630 In some embodiments, in response to receiving the incident, the agentic systemdynamically spawns the coordinating agentusing respective computational resources. For example, in response to receiving the incidentand within a predetermined time (e.g., a few seconds up to a few minutes), the agentic systemdynamically spawns the coordinating agentrespective computational resources (e.g., CPUs, memory, user interfaces, etc.). In particular, during the predetermined time, the agentic systemaccesses the computational resources, allocates necessary resources, and prevents any conflicts in resource distribution across different incidents. In some embodiments, in accordance with a determination that the incidentis received by the agentic system, the coordinating agentis dynamically spawned to execute and convene the incident. In this scenario, the coordinating agentdoes not remain idle and respective computational resources (e.g., CPUs, memory, user interfaces, etc.) used for spawning the coordinating agentare neither occupied and nor allocated unnecessarily. In some embodiments, the coordinating agentis uniquely assigned to the incidentin a one-to-one correlation. In some embodiments, the coordinating agentis assigned to one or more incidents including the incident.

662 640 642 642 1 642 652 652 1 652 652 1 642 1 642 300 640 660 632 606 640 642 606 642 652 1 652 642 352 1 652 1 642 1 642 1 642 2 642 652 1 652 1 642 1 642 2 m n n 3 FIG. In some embodiments, the collaborationincludes a workflowhaving a plurality of steps(e.g., step-to step-, where m is an integer greater than two). The one or more on-call agentsincludes a plurality of on-call agents (e.g., on-call agent-to on-call agent-, where n is an integer greater than two). Each (e.g., first on-call agent-) of the plurality of on-call agents is spawned for a respective step (e.g., first step-) of the plurality of steps. In some embodiments, similar to the configuration illustrated in the example agentic orchestration platformin, the workflowdefines, based the call, a process to generate the output datato the user. In particular, the workflowincludes the plurality of stepsthat define specific actions/activities for generating a target output for the user, such that the plurality of stepsare executed by the plurality of on-call agents (e.g., on-call agent-to on-call agent-). In some embodiments, each of the plurality of stepsis assigned to (e.g., executed by) a respective on-call agent (e.g., first on-demand agent-) that is distinct from remaining on-call agent(s) of the plurality of on-call agents. Stated another way, the plurality of on-call agents are distinct from each other, and each of the plurality of on-call agents (e.g., first on-call agent-) is spawned for a respective step (e.g., first step-) using respective computational resources. In some embodiments, one or more steps (e.g., step-and step-) of the plurality of stepsare assigned to (e.g., executed by) the same on-call agent (e.g., first on-call agent-). Stated another way, a respective on-call agent (e.g., first on-call agent-) is spawned for one or more steps (e.g., step-and step-) using respective computational resources.

652 1 642 1 102 652 1 642 1 102 102 642 1 642 2 642 642 604 m In some embodiments, in accordance with a determination that a respective on-call agent (e.g., first on-call agent-) of the plurality of on-call agents completes a respective step (e.g., step-), the agentic systemautomatically terminates the respective on-call agent to release respective computational resources used for spawning the respective on-call agent. In some embodiments, in response to detecting that a respective on-call agent (e.g., first on-call agent-) of the plurality of on-call agents completes a respective step (e.g., step-), the agentic systemautomatically terminates the respective on-call agent to release respective computational resources used for spawning the respective on-call agent. For example, the agentic systemis configured to automatically terminate a respective on-call agent in an intermediate step (e.g., step-, step-, step-) of the plurality of steps, such that the computational resourcesare dynamically allocated on an as-needed basis (e.g., when performing operations for a SOP, when resolving an issue related to a system outage, etc.).

642 102 604 642 1 652 1 642 2 652 2 652 2 652 1 604 642 102 642 In some embodiments, for each of the plurality of steps, the agentic systemdynamically spawns, using respective computational resources (e.g., from computational resources) and by a respective on-call agent, another respective on-call agent spawned for another respective step subsequent to a respective step. Stated another way, when a respective step (e.g., first step-) is assigned to a respective on-call agent (e.g., first on-call agent-) and another respective step (e.g., second step-) is assigned to another respective on-call agent (e.g., second on-call agent-), the other respective on-call agent (e.g., second on-call agent-) is dynamically spawned by the respective on-call agent (e.g., first on-call agent-) using respective computational resources (e.g., from computational resources). For example, an on-call agent (e.g., agent “EXECUTOR”) for executing a code script can be dynamically spawned by its preceding on-call agent (e.g., agent “DEVELOPER”) for developing the code script. Specifically, in this configuration, each on-call agent is specifically spawned to handle the exact requirements for each of the plurality of steps, thereby improving accuracy and reducing the likelihood of errors. Additionally, by dynamically spawning on-call agents only when needed, the agentic systemensures that computational resources (e.g., CPUs, memory, storages, etc.) are allocated efficiently and utilized only for the duration of each of the plurality of steps.

642 102 652 1 642 1 652 1 652 2 642 2 In some embodiments, for each of the plurality of steps, the agentic systemgenerates, by a respective on-call agent, respective data. Another on-call agent spawned for another respective step, subsequent to the respective step, is dynamically spawned based in part on the respective data. Stated another way, respective data generated by a respective on-call agent (e.g., first on-call agent-) for a respective step (e.g., first step-) includes information that is used by the respective on-call agent (e.g., first on-call agent-) to dynamically spawn a subsequent on-call agent (e.g., second on-call agent-) for a subsequent step (e.g., second step-). For example, the respective data generated by the respective on-call agent includes a set of system logs along with an information indicative that a summary of the system logs needs to be created. Accordingly, the respective on-call agent dynamically spawns a subsequent on-call agent (e.g., agent “SUMMARIZER”) to summarize the system logs. In another example, when the respective data generated by the respective on-call agent includes a code script, the respective on-call agent determines, based on the code script, that a follow-up execution is required, and further dynamically spawns a subsequent on-call agent (e.g., agent “EXECUTOR”) to execute the code script.

642 1 642 650 660 650 652 1 640 652 1 652 1 660 650 In some embodiments, when a respective step is an initial step (e.g., first step-) of the plurality of steps, a respective on-call agent spawned for the respective step is dynamically spawned by the coordinating agent. For example, in some embodiments, in response to convening the call, the coordinating agentdynamically spawns the first on-call agent-to initiate the workflow. In this scenario, the first on-call agent-does not remain idle and respective computational resources (e.g., CPUs, memory, user interfaces, etc.) for spawning the first on-call agent-are neither occupied and nor allocated unnecessarily prior to the callbeing convened by the coordinating agent.

642 102 102 670 606 672 102 102 102 606 670 670 606 630 606 672 672 102 606 672 606 672 630 672 134 334 1 FIG. 3 FIG. In some embodiments, for each of the plurality of steps, in accordance with a determination that a respective step requires an execution of a code script, the agentic systemtemporarily suspends the respective step. The agentic systemfurther sends, by a respective on-call agent, an authorization requestto the user. In accordance with a determination that a user authorizationis received, the agentic systemresumes, by the respective on-call agent, the respective step. For example, in accordance with a determination that a respective step requires an execution of a code script by an agent “EXECUTOR,” the agentic systemtemporarily suspends the execution. Subsequently or concurrently, the agentic systemseeks a permission from the userby sending the authorization request. In response to receiving the authorization request, the userreviews the code script and corresponding information (e.g., severity/priority level of the incident, scope of the code script), the usercreates the user authorizationfor the agent “EXECUTOR” to execute the code script. In some circumstances, the user authorizationincludes a different instruction (e.g., changing line codes, running only a specific portion of the code script). In some embodiments, a respective on-call agent cannot execute a code script independently (e.g., when executing the code script alters the state of a system). For example, when executing a code script impacts system configurations, modifies critical data, or triggers automated processes with significant consequences, the respective on-call agent is restricted from proceeding autonomously. In this situation, the agentic systemsuspends the execution of the code script until a permission/authorization is received from user. In some embodiments, the user authorizationincludes clarifications (e.g., adjustments/refinements to the code script) and/or instructions (e.g., running only a specific portion of the code script) from the user. In some embodiments, the user authorizationincludes customized instructions (e.g., conditional execution corresponding to the severity/priority level of the incident, time-based execution corresponding to a predetermined timeframe, role-based execution corresponding to access to restricted data/database). In some embodiments, the user authorizationis part of user supervision (e.g., supervisionin, user supervisionin).

652 632 606 652 606 102 652 102 652 652 606 102 652 In some embodiments, automatically terminating the one or more on-call agentsis performed in response to sending the output datato the user. For example, in a scenario where the one or more on-call agentsare assigned to analyze historical system logs for errors, in response to sending an error report to the user, the agentic systemautomatically shuts down and terminates the one or more on-call agentsto free up associated computational resources. In particular, the agentic systemautomatically terminates the one or more on-call agentswithout intentionally introducing a delay in time. In another example, in a scenario where the one or more on-call agentsare assigned to extract historical incidents for generating a SOP, in response to sending the SOP to the user, the agentic systemautomatically shuts down and terminates the one or more on-call agentsto release associated computational resources.

652 632 606 102 652 606 652 606 102 652 606 102 652 652 606 102 652 606 606 102 652 In some embodiments, automatically terminating the one or more on-call agentsis performed after a predetermined period elapses subsequent to transmitting the output datato the user. Specifically, this configuration allows for a grace period before the agentic systemterminates the one or more on-call agents, thereby ensuring the flexibility for the userto provide supervision while optimizing computational resource usage. For example, in a scenario where the one or more on-call agentsare assigned to resolve a system outage, in response to sending a resolution recommendation to the user, the agentic systeminstructs the one or more on-call agentsto remain active or idle for a predetermined period (e.g., one hour) to accommodate new system outage incident(s) received from the user. In accordance with a determination that no new incident is received within one hour, the agentic systemautomatically shuts down and terminates the one or more on-call agentsto release associated computational resources. In another example, in a scenario where the one or more on-call agentsare assigned to generate and execute a code script (e.g., a maintenance script), in response to running the code script and sending a corresponding outcome to the user, the agentic systeminstructs the one or more on-call agentsto remain active or idle for a predetermined period (e.g., 10 minutes) to accommodate a need from the userto rerun the code script or review execution logs. In accordance with a determination that no additional supervision (e.g., request to rerun the code script, request to review execution logs) is received from the user, the agentic systemautomatically shuts down and terminates the one or more on-call agentsto release associated computational resources.

652 102 102 102 In some embodiments, automatically terminating the one or more on-call agentsis performed within a predetermined period and automatically ceases after the predetermined period elapses. Specifically, this configuration provides a controllable and tunable termination window to maintain operational efficiency and flexibility for the agentic system. For example, the agentic systemis configured to periodically (e.g., every 30 minutes) detect idle on-call agent(s) and initiate a termination process that runs for a predetermined period (e.g., 10 minutes) for terminating the detected idle on-call agent(s). Once the predetermined period expires, the termination process ceases until the next scheduled check. In another example, the agentic systemis configured to periodically (e.g., every 24 hours) optimize computational resources by terminating idle on-call agent(s). A termination cycle runs for a predetermined period (e.g., one hour) to free up computational resources. After the predetermined period, no additional idle on-call agent(s) are terminated until the next scheduled optimization cycle.

630 660 650 604 630 630 650 660 630 650 660 640 In some embodiments, the incidentincludes a severity level (e.g., high-severity “S1,” medium-severity “S2,” low-severity “S3,” etc.) and/or a priority level (e.g., critical-priority “P1,” high-priority “P2,” medium-priority “P3,” low-priority “P4,” etc.). The callis convened based in part on the severity level and/or the priority level. In particular, the coordinating agent, based on the severity level and/or the priority level, dynamically allocates and optimizes the distribution of the computational resources, thereby ensuring efficient resource management and workload balancing for the incident. For example, in accordance with a determination that the incidentincludes a high-severity level “S1” and a critical-priority level “P1” outage (e.g., a system/service outage), the coordinating agentprioritizes respective computation resources (e.g., CPUs, memory, storages, computing nodes, etc.) for the calland temporarily suspends non-essential background incidents/tasks. In another example, in accordance with a determination that the incidentincludes a low-severity level “S3” and a medium-priority level “P3” event (e.g., an application malfunction, a request to summarize system logs), the coordinating agentdeprioritizes respective computation resources (e.g., CPUs, memory, storages, computing nodes, etc.) for the calland initiates the workflowduring non-peak hours.

604 604 104 106 108 110 112 114 116 118 1 FIG. In some embodiments, the computational resourcesincludes at least one of the group consisting of (i) computing resources (e.g., CPUs, GPUs, server loads, etc.), (ii) memory resources (in-memory caching, virtual machines, etc.), and (iii) cloud resources (e.g., cloud storages, network bandwidths, etc.). In some embodiments, the computational resourcesis part of the plurality of functional platformsinincluding the user platform, the AI platform, the database platform, the cloud platform, the computing platform, the device platform, the documentation platform, and the UI platform.

600 300 510 102 634 134 334 534 1 534 2 632 102 634 650 652 632 632 102 632 632 102 632 606 634 606 632 606 3 FIG. 5 FIG.B 1 FIG. 3 FIG. 5 FIG.B In some embodiments, the example incident management frameworkincorporates user supervision, similar to the example agentic orchestration platforminand the example incident management frameworkin. In particular, the agentic systemreceives user supervision(e.g., similar to supervisionin, user supervisionin, and first and second user supervisions-and-in) associated with the output data. The agentic systemfurther determines, based on the user supervisionand by a respective agent of the coordinating agentand the one or more on-call agents, whether the output datarequires updating. In accordance with a determination that the output datarequires updating, the agentic systemfurther updates the output datato form updated output data′. The agentic systemfurther transmit the updated output data′ to the user. In some embodiments, the user supervisionincludes a two-fold supervision: (i) the userreviews and provides clarifications (e.g., adjustments/refinements to output data) and (ii) the userreviews and provides authorization (e.g., a permission for executing a respective step by a respective on-call agent).

650 652 104 106 108 110 112 114 116 118 120 In some embodiments, each agent of the coordinating agentand the one or more on-call agentsis driven by a respective computational component from a plurality of computational components (e.g., data analytics, analytical models, machine-learning models, LLMs, plugins, other types of models, or a combination of various types). In some embodiments, the plurality of computational components are built using a combination of resources received from and/or stored in the plurality of functional platforms(e.g., the user platform, the AI platform, the database platform, the cloud platform, the computing platform, the device platform, the documentation platform, and/or the UI platform). In some embodiments, the plurality of computational components include at least one of the group consisting of (i) an analytical model (e.g., regression model, decision tree, clustering, etc.), (ii) an LLM (e.g., deep learning models, natural language processing, etc.), and (iii) a plugin (e.g., query plugin, automation plugin, chatbot plugin, knowledge base integration, etc.).

630 632 632 606 600 600 102 600 400 4 FIG. In some embodiments, the operations (e.g., receiving the incident, transmitting the output dataand the updated output data′ to the user) in the example incident management frameworkare performed in a graphical portal (e.g., incident dashboard, incident ticketing system, collaboration panel, reporting graphical tool, etc.). In some embodiments, the graphical portal associated with the example incident management frameworkis part of the portal agentic system of the agentic system. In some embodiments, the graphical portal associated with the example incident management frameworkis similar to the example UIin.

102 In some embodiments, the agentic systemis configured to drive various use cases, including but not limited to (i) inventory and configuration audit (e.g., automating audit processes to save time and reduce errors), (ii) error analysis and resolution (e.g., rapidly identifying and resolving errors, minimizing downtime), (iii) log summarization and prioritization (e.g., extracting critical information from logs and prioritizing alerts), (iv) SOP creation (e.g., automating creation of SOPs), (v) content validation, correction, and translation (e.g., streamlining content-related tasks), (vi) workflow a optimization (e.g., identifying and implementing improvements in existing workflows), (vii) operational readiness review (ORR) and checkpoint management (e.g., automating onboarding applications and creation of new checkpoints), (viii) global business services (GBS) onboarding (e.g., automating steps for onboarding business unit applications supported by GBS (e.g., cloud management services (CMS), infrastructure portfolio management (IPM), IT service management (ITSM), etc.)), (ix) AI-powered business process automation (BPA) (e.g., leveraging agents to offset manual and/or mundane business processes), (xi) scale-out teams (e.g., augmenting teams with agents to increase team sizes), and (xii) respective mean time to repair (MTTR) reduction (e.g., automating diagnostics, providing real-time recommendations, and/or executing predefined remediation steps).

102 102 110 102 102 102 1 FIG. In some embodiments, the agentic systemis configured to reduce MTTR for incidents by proactively searching for critical incidents. In particular, the agentic systemproactively search for critical incidents, which are collected and stored in a database (e.g., a database of the database platformin), and generated simplified, standardized resolutions. This process enables the agentic systemto retrieve the simplified, standardized resolutions directly in a shorter timeframe when resolving new critical incidents. An outcome of this process is to provide a library of simplified, standardized SOPs that are available to rapidly resolve any new critical incidents, and each simplified, standardized SOP is leveraged across IT services at scale for the same/similar critical incident. For example, the agentic systemgenerates a simplified, standardized SOP based on a total of 83 SOPs (e.g., 13 SOPs resolve respective incidents, 5 SOPs require further investigation, 65 SOPs are pending for further validation) within a total time of 1.3 mins, which provides a time saving of approximately 3.5 hours in average for each human. Without the agentic system, a process of generating a simplified, standardized SOP for these 83 SOPs may require an average of 290 hours (e.g., at least 2 hours on average for researching critical incidents, identifying issues, co-relating issues to respective root causes requires; at least 1.5 hours on average for documenting an SOP and detecting errors).

330 530 110 102 350 1 552 1 140 512 102 352 552 102 102 1 FIG. 3 FIG. 5 FIG.B Specifically, in some embodiments, a user request (e.g., the user requestand/or the incident) defines a request to reduce a respective MTTR for an incident stored in a first database (e.g., a database of the database platformin). The agentic systemgenerates, based on the user request and by an agent (e.g., the first agent-, the first on-call agent-), a workflow (e.g., the workflowinand/or the second pipelinein) that includes a respective step having a respective task for searching the incident in the first database. The agentic systemfurther process the workflow by one or more agents (e.g., the one or more on-demand agents, the plurality of on-call agents) to generate output data including a respective SOP configured to reduce the respective MTTR for the incident. For example, the agentic systemgenerates by agent(s) integrated log analytics that are used to retrieve all critical incidents. In another example, the agentic systemgenerates by agent(s) a standardized, detailed SOP for each critical incident.

102 110 102 102 1 FIG. In some embodiments, the agentic systemis configured to reduce MTTR for incidents by generating automation scripts for SOPs stored in a database (e.g., a database of the database platformin). An outcome of this process is to provide a library of reusable scripts derived from the SOPs that can be deployed in various IT service environments, and each automation script is leveraged across IT services at scale for the same/similar critical incident. For example, the agentic systemgenerates 83 scripts based on a total of 83 SOPs, where generation of each script is accomplished within a total time of 59 secs, which provides a time saving of approximately 10-20 hours for a human (e.g., with respect to time for peer review, script validation, etc.). Without the agentic system, a process of generating these 83 scripts may require an average 2,490 hours (e.g., time for researching critical incidents, identifying automation plans, creating and researching automation scripts; time for drafting and developing automation scripts using best practices; time for validating scripts for errors (e.g., peer review) and ensuring scripts are written using the latest supported framework for respective operating system(s) and critical incidents).

330 530 330 530 110 102 350 1 552 1 140 512 102 352 552 102 102 1 FIG. 3 FIG. 5 FIG.B Specifically, in some embodiments, a user request (e.g., the user requestand/or the incident) defines a user request (e.g., the user requestand/or the incident) defines a request to reduce a respective MTTR for a plurality of SOPs stored in a second database (e.g., a database of the database platformin). The agentic systemgenerates, based on the user request and by an agent (e.g., the first agent-, the first on-call agent-), a workflow (e.g., the workflowinand/or the second pipelinein) that includes a respective step having a respective task for receiving the plurality of SOPs from the second database. The agentic systemfurther process the workflow by one or more agents (e.g., the one or more on-demand agents, the plurality of on-call agents) to generate output data including a script with a set of code statements configured to reduce the respective MTTR for the plurality of SOPs. For example, the agentic systemleverages LLMs through agent(s) to generate the script that adhere to coding best practices. In another example, the agentic systemdrives agent(s) to review the script for errors and validation.

7 FIG. 700 102 700 102 700 700 102 700 510 600 102 illustrates an example self-service frameworkthat implements the agentic system, in accordance with some embodiments. In particular, the example self-service frameworkis configured as a webUI-based self-service platform that facilitates communications between users and the agentic system. In some embodiments, the example self-service frameworkdrives use cases as discussed above (e.g., MTTR reduction, log summarization and prioritization, SOP creation, etc.). In some embodiments, the example self-service frameworkis operated based on the WebUI agentic system (e.g., one of the modalities of the agentic system). In some embodiments, the example self-service frameworkis similar to the example incident management frameworkand the example incident management framework, all of which are AI-augmented and built based on the agentic system. In some embodiments, on-call agents and on-demand agents are exchangeable.

7 FIG. 102 750 1 702 730 1 706 712 710 714 714 1 714 706 710 706 730 1 702 706 710 706 730 1 702 730 1 102 750 2 732 710 732 712 714 714 1 714 102 750 1 702 732 706 732 702 102 750 1 702 730 2 706 710 706 732 706 730 2 702 706 732 706 730 2 702 730 2 102 750 2 738 710 738 710 738 738 102 750 1 702 738 706 738 702 k k In some embodiments, as shown in, the agentic systemreceives, by an interface agent-and via a webUI, a first user query-from a userthat defines a request to summarize historical datacorresponding to a critical eventassociated with a plurality of incidents(e.g., e.g., incident-to incident-, where k is an integer greater than two). For example, in a scenario where the userintends to review a history of incidents related to critical eventin domain secure session setup, the usersends the first user query-via the webUIthat defines a request to retrieve historical incident reports associated with the domain secure session setup, identify recurring patterns, and provide a summary of root causes, resolutions, and impact. In another example, in a scenario where the userintends to review a history of incidents related to critical eventassociated with email false alerts, the usersends the first user query-via the webUIthat defines a request to retrieve historical data on reported errors/incidents and provide a summary of affected accounts and corrective measures that were implemented. In response to receiving the first user query-, the agentic systemfurther generates, by an executing agent-, an event reportassociated with the critical event. For example, in some embodiments, the event reportincludes a summary of historical dataof the incidents(e.g., incident-to incident-) having incident logs (e.g., resolution history, root cause analysis, reviews, alerts, error messages, etc.). The agentic systemfurther displays, by the interface agent-and via the webUI, the event reportto the user. For example, the event reportis displayed via the webUIin various formats, including but not limited to texts, tables, files, slides, and other supported formats. The agentic systemfurther receives, by the interface agent-and via the webUI, a second user query-from the userthat defines a request to reduce a MTTR for resolving the critical event. For example, after the userreviews the event reportassociated with the domain secure session setup, the usersends the second user query-via the webUIthat defines a request to reduce a MTTR for resolving errors occurred during the domain secure session setup. In another example, after the userreviews the event reportassociated with the email false alerts, the usersends the second user query-via the webUIthat defines a request to reduce a MTTR for resolving tickets related to the email false alerts. In response to receiving the second user query-, the agentic systemfurther generates, by the executing agent-, an enhanced SOPconfigured to reduce the MTTR for resolving the critical event. In particular, the enhanced SOPis a refined and comprehensive SOP associated with the critical event. For example, the enhanced SOPstandardizes existing SOPs to include integrated steps, predefined escalation paths, and pre-allocated resources. In another example, the enhanced SOPincludes automation, such as automated feedback loops and follow-ups, automated data collections, and real-time monitoring and collaborations. The agentic systemfurther displays, by the interface agent-and via the webUI, the enhanced SOPto the user. For example, the enhanced SOPis displayed via the webUIin various formats, including but not limited to texts, tables, files, slides, and other supported formats (e.g., code scripts).

702 800 706 102 702 706 102 750 1 350 1 104 706 702 750 1 750 2 102 750 2 350 2 650 104 706 750 2 706 750 2 650 652 8 8 FIGS.A-E 3 FIG. 3 FIG. 6 FIG. 6 FIG. 6 FIG. In some embodiments, the webUI(e.g., example webUIin) serves as a visual and interactive application/website for the userto interact with the agentic system(e.g., through a web browser). In particular, the webUIenhances self-service experiences by providing an efficient platform (e.g., featuring AI augmented experiences, task-specialized interfaces, 24/7 accessibility, etc.) for the userto send user queries and obtain results from the agentic system. In some embodiments, the interface agent-(e.g., similar to first agent-in) is built using computational resources from the plurality of functional platformsand configured to interact with the userand navigate the webUI. Moreover, the interface agent-is configured to communicate with other agents (e.g., executing agent-, other on-demand/on-call agents) of the agentic system. In some embodiments, the executing agent-(e.g., similar to second agent-inand coordinating agentin) is built using computational resources from the plurality of functional platformsand configured to execute tasks and actions (e.g., workflow automation, real-time computation and analysis, system incident/error discovery, etc.) corresponding to user queries from the user. Moreover, the executing agent-functions as a backend executor and does not interact directly with the user. In some embodiments, the executing agent-includes a coordinating agent (e.g., similar to coordinating agentin) and one or more on-call agents (e.g., similar to one or more on-call agents). In particular, the one or more on-call agents are dynamically spawned by the coordinating agent (e.g., similar to the dynamic spawning configuration in reference to).

712 716 716 1 716 716 1 716 714 1 714 710 716 1 714 1 716 716 k k k In some embodiments, the historical dataincludes a plurality of SOPs(e.g., SOP-to SOP-, where k is an integer greater than two). Each (e.g., SOP-) of the plurality of SOPsis associated with a corresponding incident (e.g., incident-) of the plurality of incidents. For example, during the occurrence of each incident associated with the critical event, a corresponding SOP is created (e.g., by a user) to document necessary procedures and steps. In some circumstances, the corresponding SOP functions as a temporary resolution and may not be sufficiently precise or comprehensive. In other circumstances, the corresponding SOP (e.g., SOP-) associated with an incident (e.g., incident-) is a direct or closely replicated copy of another SOP (e.g., SOP-) associated with another incident (e.g., incident-).

712 718 718 1 718 718 1 718 714 1 714 718 750 2 706 732 k In some embodiments, the historical dataincludes a plurality of incident logs(e.g., incident log-to incident log-, where k is an integer greater than two). Each (e.g., incident log-) of the plurality of incident logsis associated with a corresponding incident (e.g., incident-) of the plurality of incidentsand has a corresponding resolution history. For example, in some embodiments, a respective incident log includes resolution history (e.g., resolution steps, temporary solutions, rollback actions, etc.), root cause analysis (e.g., cause identifications, contributing factors, mitigation strategies, etc.), reviews (e.g., internal/external feedback, summaries, etc.), alerts (e.g., system alerts, escalations, notifications, etc.), error messages (e.g., error codes, pop-ups, failure reports, etc.), and other aspects (e.g., severity/priority levels, resource usages, time to resolve, etc.). In particular, the plurality of incident logsare summarized by the executing agent-and presented to the useras part of the event report.

730 1 102 750 1 730 1 750 2 102 750 2 730 1 712 704 102 750 2 732 712 102 750 2 732 750 1 704 718 704 704 712 710 704 102 704 104 110 1 FIG. In some embodiments, in response to receiving the first user query-, the agentic systemtransmits, by the interface agent-, the first user query-to the executing agent-. The agentic systemfurther retrieves, by the executing agent-and based on the first user query-, the historical datafrom a repository database. The agentic systemfurther generates, by the executing agent-, the event reportto summarize the historical data. The agentic systemfurther sends, by the executing agent-, the event reportto the interface agent-. In some embodiments, the repository databasestores and archives records of the plurality of incident logs. For example, the repository databaseincludes a schema to enable efficient data retrieval and query performance. In another example, the repository databaseincludes a metadata database that archives metadata of the historical dataassociated with the critical event. In some embodiments, the repository databasestores and archives records of incidents corresponding to one or more critical events associated with the agentic system. In some embodiments, the repository databaseis part of the plurality of functional platformsin(e.g., database platform).

730 2 102 750 1 730 2 750 2 102 750 2 730 2 712 738 710 102 750 2 738 750 1 750 2 712 738 750 2 712 738 In some embodiments, in response to receiving the second user query-, the agentic systemtransmits, by the interface agent-, the second user query-to the executing agent-. The agentic systemfurther analyzes, by the executing agent-and based on the second user query-, the historical datato generate the enhanced SOPconfigured to reduce the MTTR for resolving the critical event. The agentic systemfurther sends, by the executing agent-, the enhanced SOPto the interface agent-. For example, in an IT server outage scenario, the executing agent-analyzes the historical data(e.g., historical incident logs, previous resolution steps) to generate the enhanced SOPthat includes predefined reboot procedures and automated system diagnostics to minimize the MTTR (e.g., a system downtime). In another example, in a false alert scenario, the executing agent-analyzes the historical data(e.g., historical false alerts, previous mitigation steps) to generate the enhanced SOPthat includes refined detection procedures and automated system diagnostics to minimize the MTTR (e.g., a response time).

738 740 738 102 712 102 750 2 740 102 750 2 740 706 102 750 2 740 740 134 334 534 1 534 2 634 1 FIG. 3 FIG. 5 FIG.B 6 FIG. In some embodiments, the enhanced SOPincludes a code scriptconfigured to generate a textual SOP corresponding to the enhanced SOP. When the agentic systemanalyzes the historical data, the agentic systemvalidates, by the executing agent-, the code scriptto minimize errors. For example, the agentic systemleverages LLMs through the executing agent-to generate the code scriptthat automatically generates a textual SOP to the user. In another example, the agentic systemdrives the executing agent-to review and validate the code scriptfor errors and validation. In some embodiments, validation of the code scriptrequires a user supervision (e.g., similar to supervisionin, user supervisionin, first and second user supervisions-and-in, and user supervisionin).

750 1 750 2 104 106 108 110 112 114 116 118 120 In some embodiments, each agent of the interface agent-and the executing agent-is driven by a respective computational component from a plurality of computational components (e.g., data analytics, analytical models, machine-learning models, LLMs, plugins, other types of models, or a combination of various types). In some embodiments, the plurality of computational components are built using a combination of resources received from and/or stored in the plurality of functional platforms(e.g., the user platform, the AI platform, the database platform, the cloud platform, the computing platform, the device platform, the documentation platform, and/or the UI platform). In some embodiments, the plurality of computational components include at least one of the group consisting of (i) an analytical model (e.g., regression model, decision tree, clustering, etc.), (ii) an LLM (e.g., deep learning models, natural language processing, etc.), and (iii) a plugin (e.g., query plugin, automation plugin, chatbot plugin, knowledge base integration, etc.).

8 8 FIGS.A-E 800 102 800 702 700 800 102 800 800 102 illustrate an example webUIof the agentic system, in accordance with some embodiments. In particular, the example webUIis configured to facilitate the functionality of the webUIof the example self-service framework. In some embodiments, the example webUIis configured as a webUI-based self-service platform that facilitates communications between users and the agentic system. In some embodiments, the example webUIdrives user-system interactions for use cases as discussed above (e.g., MTTR reduction, log summarization and prioritization, SOP creation, etc.). In some embodiments, the example webUIis operated based on the WebUI agentic system (e.g., one of the modalities of the agentic system).

8 FIG.A 7 FIG. 801 800 801 810 820 810 820 822 824 730 1 730 2 illustrates a screenshotof a main user interface of the example webUI. In particular, the screenshotincludes a history paneand a home panedisplayed concurrently. The history panedisplays chat history (e.g., recent chats). The home panedisplays a plurality of user query examplesand includes an input tabconfigured to receive user queries (e.g., first user query-and second user query-in).

8 FIG.B 8 FIG.B 7 FIG. 802 820 800 826 828 102 826 826 826 102 828 828 828 718 illustrates a screenshotof the home paneof the example webUIdisplaying a user queryfrom a user and an event reportgenerated by the agentic systemcorresponding to the user query. In particular, the user querydefines a request to summarize historical data corresponding to an event associated with a plurality of incidents (e.g., “list insights about incidents relating to hCue application”). In response to receiving the user query, the agentic systemfurther generates (e.g., by one or more agents), the event reportassociated with the event (e.g., “hCue application”). As shown in, the event reportincludes incident description, incident start time, resolution, root cause, solution proposal, problem number, problem stage, additional incident, resolution time, and final root cause. In some embodiments, the information provided in the event reportis obtained from incident log(s) (e.g., plurality of incident logsin) associated with the event (e.g., “hCue application”).

8 FIG.C 8 FIG.C 7 FIG. 803 820 800 830 832 102 830 830 830 102 832 832 834 832 718 illustrates another screenshotof the home paneof the example webUIdisplaying a user queryfrom a user and an event reportgenerated by the agentic systemcorresponding to the user query. In particular, the user querydefines a request to summarize historical data corresponding to an event associated with a plurality of incidents (e.g., “list incidents in 2024”). In response to receiving the user query, the agentic systemfurther generates (e.g., by one or more agents), the event reportassociated with the event (e.g., timeframe of “2024”). As shown in, the event reportincludes a short summary of a total of 403 incidents, a brief description of three highlighted incidents (e.g., “INC2646633,” “INC2647482,” and “INC2650314”), and an optionto download the results associated with these 403 incidents. In some embodiments, the information provided in the event reportis obtained from incident log(s) (e.g., plurality of incident logsin) associated with the event (e.g., timeframe of “2024”).

8 FIG.D 7 FIG. 804 820 800 836 102 836 838 836 718 illustrates another screenshotof the home paneof the example webUIdisplaying an event reportgenerated by the agentic systemcorresponding to a user query. Similarly, the event reportincludes three highlighted incidents and an optionto download the results associated with a total of 361 incidents. In some embodiments, the information provided in the event reportis obtained from incident log(s) (e.g., plurality of incident logsin).

8 FIG.E 7 FIG. 805 850 800 836 102 850 820 810 850 852 852 854 856 858 860 850 718 illustrates a screenshotof the result paneof the example webUIdisplaying query results (e.g., as part of the event report) generated by the agentic systemcorresponding to a user query. In some embodiments, the result paneis displayed concurrently with the home paneand/or the history pane. The result panedisplays a summary tablecorresponding to the query results. The summary tableincludes a “number” column(e.g., serial numbers of incidents), a “created_at” column(e.g., time when incidents were created by a human or an agent), a “description column(e.g., a brief summary of each incident), and a “priority” column(e.g., priority levels such as “critical” and “high”). In some embodiments, the information provided in the result paneis obtained from incident log(s) (e.g., plurality of incident logsin).

9 FIG. 2 FIG. 2 FIG. 900 900 200 900 210 is a flow diagram illustrating a methodof orchestrating agents for a user task, in accordance with some embodiments. The methodmay be performed at a computer system (e.g., the computer system,) having one or more processors and memory storing instructions for execution by the one or more processors. In some embodiments, the methodis performed by executing instructions stored in memory (e.g., memory,) of the computer system.

In some embodiments, each of the agents described below is an artificial intelligence agent. In some embodiments, each of the agents described below includes an LLM. In some embodiments, each of the events described below is a critical event (e.g., associated with critical and high-priority incidents) and requires computation (e.g., real-time user/incident data analysis, code script generations, resource-intensive computations/inquiries, etc.).

900 902 330 350 1 140 140 904 342 900 906 140 350 2 352 342 908 352 1 352 900 910 140 352 332 900 912 334 332 350 1 900 914 334 350 2 332 900 332 916 332 900 918 332 306 350 1 350 1 352 920 (A1-a) The methodincludes generating (operation), based on a user requestand by a first agent-, a workflow. The workflowincludes (operation) a plurality of steps. The methodfurther includes generating (operation), based on the workflowand by a second agent-, one or more on-demand agents. Each of the plurality of stepsis assigned (operation) to a respective on-demand agent (e.g., a first on-demand agent-) of the one or more on-demand agents. The methodfurther includes analyzing (operation) the workflowby the one or more on-demand agentsto generate output data. The methodfurther includes receiving (operation) user supervisionassociated with the output databy the first agent-. The methodfurther includes determining (operation), based on the user supervisionand by the second agent-, whether the output datarequires updating. The methodfurther includes in accordance with a determination that the output datarequires updating, updating (operation) the output data. The methodfurther includes displaying (operation) the updated output data′ to a user. Each agent of the first agent-, the second agent-, and the one or more on-demand agentsis driven (operation) by a respective computational component from a plurality of computational components.

900 330 106 350 1 140 140 342 900 140 350 2 352 900 140 352 332 350 2 140 342 642 1 352 1 352 352 1 642 1 362 1 900 350 2 332 350 1 900 350 1 332 106 900 334 332 900 350 1 334 350 2 900 334 350 2 332 900 332 352 332 332 350 2 900 350 2 332 350 1 900 350 1 332 106 350 1 350 2 352 (A1-b) In some embodiments, the methodincludes instantiating (e.g., generating), based on a request (e.g., user request) from a userand by an external interface artificial intelligence agent (e.g., first agent-), a workflow. The workflowincludes a plurality of stepsconfigured to resolve a critical computing event. The methodfurther includes instantiating (e.g., generating), based on the workflowand by an internal orchestrating artificial intelligence agent (e.g., second agent-), one or more on-demand artificial intelligence agents (e.g., one or more on-demand agents). The methodfurther includes executing the workflowby the one or more on-demand artificial intelligence agents (e.g., one or more on-demand agents) to generate output datafor the internal orchestrating artificial intelligence agent (e.g., second agent-). Executing the workflowincludes, for each of the plurality of steps: assigning a respective step (e.g., first step-) to a respective on-demand artificial intelligence agent (e.g., a first on-demand agent-) of the one or more on-demand artificial intelligence agents (e.g., one or more on-demand agents); and executing, by the respective on-demand artificial intelligence agent (e.g., a first on-demand agent-), the respective step (e.g., first step-) to generate respective data (e.g., respective data-). The methodfurther includes transmitting, by the internal orchestrating artificial intelligence agent (e.g., second agent-), the output datato the external interface artificial intelligence agent (e.g., first agent-). The methodfurther includes displaying, by the external interface artificial intelligence agent (e.g., first agent-), the output datato the user. The methodfurther includes receiving user supervisioncorresponding to the critical computing event and the output data. The methodfurther includes transmitting, by the external interface artificial intelligence agent (e.g., first agent-), the user supervisionto the internal orchestrating artificial intelligence agent (e.g., second agent-). The methodfurther includes determining, based on the user supervisionand by the internal orchestrating artificial intelligence agent (e.g., second agent-), whether the output datarequires updating. The methodfurther includes in accordance with a determination that the output datarequires updating, updating, by the one or more on-demand artificial intelligence agents (e.g., one or more on-demand agents), the output datato generate updated output data′ for the internal orchestrating artificial intelligence agent (e.g., second agent-). The methodfurther includes transmitting, by the internal orchestrating artificial intelligence agent (e.g., second agent-), the updated output data′ to the external interface artificial intelligence agent (e.g., first agent-). The methodfurther includes displaying, by the external interface artificial intelligence agent (e.g., first agent-), the updated output data′ to the user. Each artificial intelligence agent of the external interface artificial intelligence agent (e.g., first agent-), the internal orchestrating artificial intelligence agent (e.g., second agent-), and the one or more on-demand artificial intelligence agents (e.g., one or more on-demand agents) is distinct from every other artificial intelligence agent and includes a large-language model.

350 1 306 350 2 350 2 350 1 352 140 (A2-a) In some embodiments of A1-a, the first agent-is configured to communicate data with the userand the second agent-. The second agent-is configured to communicate data with the first agent-and supervise the one or more on-demand agentsbased on the workflow.

350 1 106 350 2 350 2 350 1 352 140 (A2-b) In some embodiments of A1-b, the external interface artificial intelligence agent (e.g., first agent-) is configured to communicate data with the userand the internal orchestrating artificial intelligence agent (e.g., second agent-). The internal orchestrating artificial intelligence agent (e.g., second agent-) is configured to communicate data with the external interface artificial intelligence agent (e.g., first agent-) and orchestrate the one or more on-demand artificial intelligence agents (e.g., one or more on-demand agents) based on the workflow.

140 330 306 140 (A3-a) In some embodiments of A1-a to A2-a, generating the workflowincludes receiving a user query associated with the user requestfrom the user, identifying, based on the user query, a user intent, and creating, based on the user intent, the workflow.

140 330 106 140 (A3-b) In some embodiments of A1-b to A2-b, instantiating (e.g., generating) the workflowincludes receiving a user query associated with the request (e.g., user request) from the user, identifying, based on the user query, a user intent, and creating, based on the user intent, the workflow.

342 352 342 (A4-a) In some embodiments of A1-a to A3-a, each of the plurality of stepsincludes a respective task message identifying a respective task. Generating the one or more on-demand agentsincludes for each of the plurality of steps: analyzing the respective task message, and identifying, based on the analyzed respective task message, the respective on-demand agent.

342 352 342 s (A4-b) In some embodiments of A1-b to A3-b, each of the plurality of stepsincludes a respective task message identifying a respective task. Instantiating (e.g., generating) the one or more on-demand artificial intelligence agents (e.g., one or more on-demand agents) includes: for each of the plurality of step: analyzing the respective task message; and identifying, based on the analyzed respective task message, the respective on-demand artificial intelligence agent.

352 2 352 352 1 352 (A5-a) In some embodiments of A1-a to A4-a, a respective on-demand agent (e.g., a second on-demand agent-) of the one or more on-demand agentsis dynamically created by another respective on-demand agent (e.g., a first on-demand agent-) of the one or more on-demand agents.

352 2 352 352 1 352 (A5-b) In some embodiments of A1-b to A4-b, a respective on-demand artificial intelligence agent (e.g., a second on-demand agent-) of the one or more on-demand artificial intelligence agents (e.g., one or more on-demand agents) is dynamically created by another respective on-demand artificial intelligence agent (e.g., a first on-demand agent-) of the one or more on-demand artificial intelligence agents (e.g., one or more on-demand agents).

140 342 352 1 362 1 350 2 332 (A6-a) In some embodiments of A1-a to A5-a, analyzing the workflowincludes: for each of the plurality of steps, processing the respective task by the respective on-demand agent (e.g., a first on-demand agent-) to generate respective data (e.g., respective data-); and generating, based on the respective data and by the second agent-, the output data.

140 342 352 1 362 1 352 2 352 352 342 332 n m (A6-b) In some embodiments of A1-b to A5-b, executing the workflowincludes: for each of the plurality of steps: executing, by the respective on-demand artificial intelligence agent (e.g., a first on-demand agent-), the respective task to generate the respective data (e.g., respective data-) for another respective on-demand artificial intelligence agent (e.g., a second on-demand agent-) that processes another respective task subsequent to the respective task; and generating, based on the respective data from a corresponding on-demand artificial intelligence agent (e.g., a last on-demand agent-) that is assigned to a last step agent (e.g., a last step-) of the plurality of steps, the output data.

362 1 352 2 (A7-a) In some embodiments of A1-a to A6-a, the respective data (e.g., respective data-) includes a respective communication message for another respective on-demand agent (e.g., a second on-demand agent-) that processes another respective task subsequent to the respective task.

352 2 (A7-b) In some embodiments of A1-b to A6-b, the respective data includes a respective communication message for another respective on-demand artificial intelligence agent (e.g., a second on-demand agent-) that processes another respective task subsequent to the respective task.

334 332 332 306 350 1 336 334 332 (A8-a) In some embodiments of A1-a to A7-a, receiving the user supervisionassociated with the output dataincludes: displaying the output datato the userby the first agent-; and receiving a user inputincluding the user supervisionthat identifies a correctness of the output data.

334 336 334 332 (A8-b) In some embodiments of A1-b to A7-b, receiving the user supervisionincludes receiving a user inputincluding the user supervisionthat identifies a correctness of the output data.

332 350 2 334 334 352 332 (A9-a) In some embodiments of A1-a to A8-a, determining whether the output datarequires updating includes: identifying, by the second agent-, a respective on-demand agent associated with the user supervision; and determining, based on the user supervisionand by the respective on-demand agent of the one or more on-demand agents, whether the output datarequires updating.

332 350 2 334 334 352 332 (A9-b) In some embodiments of A1-b to A8-b, determining whether the output datarequires updating includes: identifying, by the internal orchestrating artificial intelligence agent (e.g., second agent-), a respective on-demand artificial intelligence agent associated with the user supervision; and determining, based on the user supervisionand by the respective on-demand artificial intelligence agent of the one or more on-demand artificial intelligence agents (e.g., one or more on-demand agents), whether the output datarequires updating.

332 334 334 350 2 332 (A10-a) In some embodiments of A1-a to A9-a, determining whether the output datarequires updating includes in response to receiving the user supervision, determining, based on the user supervisionand by the second agent-, whether the output datarequires updating.

332 334 334 350 2 332 (A10-b) In some embodiments of A1-b to A9-b, determining whether the output datarequires updating includes in response to receiving the user supervision, determining, based on the user supervisionand by the internal orchestrating artificial intelligence agent (e.g., second agent-), whether the output datarequires updating.

332 334 352 (A11-a) In some embodiments of A1-a to A10-a, updating the output dataincludes updating, based on the user supervision, a respective on-demand agent of the one or more on-demand agents.

332 334 352 (A11-b) In some embodiments of A1-b to A10-b, updating the output dataincludes updating, based on the user supervision, a respective on-demand artificial intelligence agent of the one or more on-demand artificial intelligence agents (e.g., one or more on-demand agents).

900 350 1 350 2 (A12-a) In some embodiments of A1-a to A11-a, the methodfurther includes: iteratively receiving respective user supervision associated with respective output data by the first agent-; determining, based on the respective user supervision and by the second agent-, whether the respective output data requires updating; and in accordance with a determination that the respective output data requires updating, updating the respective output data.

900 350 350 2 (A12-b) In some embodiments of A1-b to A11-b, the methodfurther includes: iteratively receiving respective user supervision corresponding to the critical computing event and respective output data by the external interface artificial intelligence agent (e.g., first agent); determining, based on the respective user supervision and by the internal orchestrating artificial intelligence agent (e.g., second agent-), whether the respective output data requires updating; and in accordance with a determination that the respective output data requires updating, updating, by the one or more on-demand artificial intelligence agents, the respective output data to generate respective updated output data for the internal orchestrating artificial intelligence agent.

(A13-a) In some embodiments of A1-a to A12-a, the plurality of computational components include at least one of the group consisting of (i) an analytical model, (ii) a large-language model, and (iii) a plugin.

350 1 350 2 352 (A13-b) In some embodiments of A1-b to A12-b, each artificial intelligence agent of the external interface artificial intelligence agent (e.g., first agent-), the internal orchestrating artificial intelligence agent (e.g., second agent-), and the one or more on-demand artificial intelligence agents (e.g., one or more on-demand agents) further includes an analytical model or a plugin.

330 140 (A14-a) In some embodiments of A1-a to A13-a, the user requestdefines a request to reduce a respective mean time to repair (MTTR) for an incident stored in a first database. The output data include a respective standard operating procedure (SOP) configured to reduce the respective MTTR for the incident. The workflowincludes a respective step having a respective task for searching the incident in the first database.

330 140 (A14-b) In some embodiments of A1-b to A13-b, the request (e.g., user request) from the user defines a request to reduce a respective mean time to repair (MTTR) for a computing incident stored in a first database. The output data include a respective standard operating procedure (SOP) configured to reduce the respective MTTR for the computing incident. The workflowincludes a respective step having a respective task for searching the computing incident in the first database.

330 140 (A15-a) In some embodiments of A1-a to A14-a, the user requestdefines a request to reduce a respective MTTR for a plurality of SOPs stored in a second database, the output data include a script with a set of code statements configured to reduce the respective MTTR for the plurality of SOPs. The workflowincludes a respective step having a respective task for receiving the plurality of SOPs from the second database.

330 140 (A15-b) In some embodiments of A1-b to A14-b, the request (e.g., user request) from the user defines a request to reduce a respective MTTR for a plurality of SOPs stored in a second database. The output data include a script with a set of code statements configured to reduce the respective MTTR for the plurality of SOPs. The workflowincludes a respective step having a respective task for receiving the plurality of SOPs from the second database.

350 2 (A16-a) In some embodiments of A1-a to A15-a, the second agent-is in compliance with a remote procedure call (RPC) framework for external functions.

350 2 (A16-b) In some embodiments of A1-b to A15-b, the internal orchestrating artificial intelligence agent (e.g., second agent-) is in compliance with a remote procedure call (RPC) framework for external functions.

140 (A17-a) In some embodiments of A1-a to A16-a, the workflowincludes a schema in form of a JavaScript Object Notation (JSON).

140 (A17-b) In some embodiments of A1-b to A16-b, the workflowincludes a schema in form of a JavaScript Object Notation (JSON).

140 330 342 342 (A18-a) In some embodiments of A1-a to A17-a, generating the workflowincludes: parsing the user requestto generate an abstract syntax tree (AST); analyzing the AST to identify the plurality of steps; and generate the schema based on the plurality of steps.

330 342 342 (A18-b) In some embodiments of A1-b to A17-b, instantiating (e.g., generating) the workflow includes: parsing the request (e.g., user request) from the user to generate an abstract syntax tree (AST); analyzing the AST to identify the plurality of steps; and generate a schema based on the plurality of steps.

(B1-a) In accordance with some embodiments, a computer system includes one or more processors memory storing one or more programs. The one or more programs are configured to be executed by the one or more processors. The one or more programs include instructions for performing the method of any of A1-a to A18-a.

(B1-b) In accordance with some embodiments, a computer system includes one or more processors memory storing one or more programs. The one or more programs are configured to be executed by the one or more processors. The one or more programs include instructions for performing the method of any of A1-b to A18-b.

(C1-a) A non-transitory computer readable storage medium storing one or more programs. The one or more programs include instructions that, when executed by a computer system that includes one or more processors, cause the one or more processors to perform the method of any of A1-a to A18-a.

(C1-b) A non-transitory computer readable storage medium storing one or more programs. The one or more programs include instructions that, when executed by a computer system that includes one or more processors, cause the one or more processors to perform the method of any of A1-b to A18-b.

10 FIG. 2 FIG. 2 FIG. 1000 1000 200 1000 210 is a flow diagram illustrating a methodof orchestrating agents for resolving incidents, in accordance with some embodiments. The methodmay be performed at a computer system (e.g., the computer system,) having one or more processors and memory storing instructions for execution by the one or more processors. In some embodiments, the methodis performed by executing instructions stored in memory (e.g., memory,) of the computer system.

102 In some embodiments, each of the agents described below is an artificial intelligence agent. In some embodiments, each of the agents described below includes an LLM. In some embodiments, each of the events described below is a critical event (e.g., associated with critical and high-priority incidents) and requires computation (e.g., real-time user/incident data analysis, code script generations, resource-intensive computations/inquiries, etc.). In some embodiments, the usage status described below includes the current state of resource utilization within the system (e.g., agentic system), providing insights into a dynamic consumption of computational and storage resources (e.g., percentage of resource occupation, such as CPU utilization, memory usage, storage consumption, network bandwidth usage, etc.). In particular, the usage status provides metrics that help assess the system's real-time performance, detect potential resource bottlenecks, and optimize resource allocation for efficient operation.

1000 1002 606 630 631 1000 1004 630 650 660 662 1000 1006 604 104 652 662 1000 1008 652 632 1000 1010 632 606 1000 1012 652 604 1 FIG. (D1-a) The methodincludes receiving (operation), from a user, an incidentdefining a target issueto be addressed. The methodfurther includes convening (operation) in real-time, based on the incidentand by a coordinating agent, a callthat defines a collaboration. The methodfurther includes dynamically spawning (operation), using computational resources(e.g., resource of functional platformsin), one or more on-call agentscorresponding to the collaboration. The methodfurther includes generating (operation), by the one or more on-call agents, output data. The methodfurther includes transmitting (operation) the output datato the user. The methodfurther includes automatically terminating (operation) the one or more on-call agentsby releasing the computational resources.

1000 630 631 1000 630 650 660 662 1000 604 104 662 1000 604 652 662 1000 652 632 1000 632 606 1000 104 1000 652 604 650 652 1 FIG. 1 FIG. (D1-b) In some embodiments, the methodincludes receiving, from a user, a critical computing incident (e.g., incident) defining a target issueto be addressed. The methodfurther includes instantiating (e.g., generating) in real-time, based on the critical computing incident (e.g., incident) and by an interface coordinating artificial intelligence agent (e.g., coordinating agent), a callthat defines a collaboration. The methodfurther includes dynamically allocating a set of computational resources (e.g., computational resources) from a pool of computational resources (e.g., resource of functional platformsin) to the collaboration. The methodfurther includes dynamically spawning, using the set of computational resources (e.g., computational resources), one or more on-call artificial intelligence agents (e.g., one or more on-call agents) corresponding to the collaboration. The methodfurther includes generating, by the one or more on-call artificial intelligence agents (e.g., one or more on-call agents), output data. The methodfurther includes transmitting the output datato the user. The methodfurther includes automatically monitoring a usage status (e.g., percentage of resource occupation, such as CPU utilization, memory usage, storage consumption, network bandwidth usage, etc.) of the pool of computational resources (e.g., resource of functional platformsin). The methodfurther includes automatically terminating, based on the usage status, the one or more on-call artificial intelligence agents (e.g., one or more on-call agents) by releasing the set of computational resources (e.g., computational resources). Each artificial intelligence agent of the interface coordinating artificial intelligence agent (e.g., coordinating agent) and the one or more on-call artificial intelligence agents (e.g., one or more on-call agents) is distinct from every other artificial intelligence agent and includes a large-language model.

1000 630 650 (D2-a) In some embodiments of D1-a, the methodfurther includes in response to receiving the incident, dynamically spawning the coordinating agent.

1000 630 650 (D2-b) In some embodiments of D1-b, the methodfurther includes in response to receiving the critical computing incident (e.g., incident), dynamically spawning the interface coordinating artificial intelligence agent (e.g., coordinating agent).

662 640 642 652 652 1 652 652 1 642 1 642 n (D3-a) In some embodiments of D1-a to D2-a, the collaborationincludes a workflowhaving a plurality of steps. The one or more on-call agentsincludes a plurality of on-call agents (e.g., on-call agent-to on-call agent-, where n is an integer greater than two). Each (e.g., first on-call agent-) of the plurality of on-call agents is spawned for a respective step (e.g., first step-) of the plurality of steps.

662 640 642 652 652 1 652 652 1 642 1 642 n (D3-b) In some embodiments of D1-b to D2-b, the collaborationincludes a workflowhaving a plurality of steps. The one or more on-call artificial intelligence agents (e.g., on-call agents) includes a plurality of on-call artificial intelligence agents (e.g., on-call agent-to on-call agent-, where n is an integer greater than two). Each (e.g., first on-call agent-) of the plurality of on-call artificial intelligence agents is spawned for a respective step (e.g., first step-) of the plurality of steps.

1000 642 604 (D4-a) In some embodiments of D1-b to D3-b, the methodfurther includes, for each of the plurality of steps: dynamically spawning, using respective computational resources (e.g., from computational resources) and by a respective on-call agent, another respective on-call agent spawned for another respective step subsequent to a respective step.

1000 642 604 (D4-b) In some embodiments of D1-b to D3-b, the methodfurther includes, for each of the plurality of steps: dynamically spawning, using respective computational resources (e.g., from computational resources) of the set of computational resources and by a respective on-call artificial intelligence agent, another respective on-call artificial intelligence agent spawned for another respective step subsequent to a respective step.

1000 642 (D5-a) In some embodiments of D1-a to D4-a, the methodfurther includes, for each of the plurality of steps: generating, by the respective on-call agent, respective data; the other on-call agent spawned for the other respective step is dynamically spawned based in part on the respective data.

1000 642 (D5-b) In some embodiments of D1-b to D4-b, the methodfurther includes, for each of the plurality of steps: generating, by the respective on-call artificial intelligence agent, respective data; the other on-call artificial intelligence agent spawned for the other respective step is dynamically spawned based in part on the respective data

642 1 642 650 (D6-a) In some embodiments of D1-a to D5-a, when a respective step is an initial step (e.g., first step-) of the plurality of steps, a respective on-call agent spawned for the respective step is dynamically spawned by the coordinating agent.

642 1 642 650 (D6-b) In some embodiments of D1-b to D5-b, when a respective step is an initial step (e.g., first step-) of the plurality of steps, a respective on-call artificial intelligence agent spawned for the respective step is dynamically spawned by the interface coordinating artificial intelligence agent (e.g., coordinating agent).

1000 642 670 606 672 (D7-a) In some embodiments of D1-a to D6-a, the methodincludes, for each of the plurality of steps: in accordance with a determination that a respective step requires an execution of a code script, temporarily suspending the respective step; sending, by a respective on-call agent, an authorization requestto the user; and in accordance with a determination that a user authorizationis received, resuming, by the respective on-call agent, the respective step.

1000 642 670 606 672 (D7-b) In some embodiments of D1-b to D6-b, the methodincludes, for each of the plurality of steps: in accordance with a determination that a respective step requires an execution of a code script, temporarily suspending the respective step; sending, by a respective on-call artificial intelligence agent, an authorization requestto the user; and in accordance with a determination that a user authorizationis received, resuming, by the respective on-call artificial intelligence agent, the respective step.

652 632 606 (D8-a) In some embodiments of D1-a to D7-a, automatically terminating the one or more on-call agentsis performed in response to sending the output datato the user.

652 (D8-b) In some embodiments of D1-b to D7-b, automatically terminating the one or more on-call artificial intelligence agents (e.g., on-call agents) is performed in response to sending the output data to the user

652 632 606 (D9-a) In some embodiments of D1-a to D8-a, automatically terminating the one or more on-call agentsis performed after a predetermined period elapses subsequent to transmitting the output datato the user.

652 (D9-b) In some embodiments of D1-b to D8-b, automatically terminating the one or more on-call artificial intelligence agents (e.g., on-call agents) is performed after a predetermined period elapses subsequent to transmitting the output data to the user.

652 (D10-a) In some embodiments of D1-a to D9-a, automatically terminating the one or more on-call agentsis performed within a predetermined period and automatically ceases after the predetermined period elapses.

652 (D10-b) In some embodiments of D1-b to D9-b, automatically terminating the one or more on-call artificial intelligence agents (e.g., on-call agents) is performed within a predetermined period and automatically ceases after the predetermined period elapses

630 660 (D11-a) In some embodiments of D1-a to D10-a, the incidentincludes a severity level (e.g., high-severity “S1,” medium-severity “S2,” low-severity “S3,” etc.) and/or a priority level (e.g., critical-priority “P1,” high-priority “P2,” medium-priority “P3,” low-priority “P4,” etc.). The callis convened based in part on the severity level and/or the priority level.

630 660 (D11-b) In some embodiments of D1-b to D10-b, the critical computing incident (e.g., incident) includes a severity level (e.g., high-severity “S1,” medium-severity “S2,” low-severity “S3,” etc.) and/or a priority level (e.g., critical-priority “P1,” high-priority “P2,” medium-priority “P3,” low-priority “P4,” etc.). The callis convened based in part on the severity level and/or the priority level.

(D12-a) In some embodiments of D1-a to D11-a, the computational resources includes at least one of the group consisting of (i) computing resources, (ii) memory resources, and (iii) cloud resources.

(D12-b) In some embodiments of D1-b to D11-b, the set of computational resources includes at least one of the group consisting of (i) computing resources, (ii) memory resources, and (iii) cloud resources

1000 634 632 1000 634 650 652 632 1000 632 1000 632 606 (D13-a) In some embodiments of D1-a to D12-a, the methodincludes receiving user supervisionassociated with the output data. The methodfurther includes determining, based on the user supervisionand by a respective agent of the coordinating agentand the one or more on-call agents, whether the output datarequires updating. The methodfurther includes in accordance with a determination that the output datarequires updating, updating the output data. The methodfurther includes transmitting the updated output data′ to the user.

1000 634 632 1000 634 650 652 632 1000 632 1000 632 606 (D13-b) In some embodiments of D1-b to D12-b, the methodincludes receiving user supervisionassociated with the output data. The methodfurther includes determining, based on the user supervisionand by a respective artificial intelligence agent of the interface coordinating artificial intelligence agent (e.g., coordinating agent) and the one or more on-call artificial intelligence agents (e.g., one or more on-call agents), whether the output datarequires updating. The methodfurther includes in accordance with a determination that the output datarequires updating, updating the output data. The methodfurther includes transmitting the updated output data′ to the user.

650 652 (D14-a) In some embodiments of D1-a to D13-a, each agent of the coordinating agentand the one or more on-call agentsis driven by a respective computational component.

650 652 (D14-b) In some embodiments of D1-b to D13-b, each artificial intelligence agent of the interface coordinating artificial intelligence agent (e.g., coordinating agent) and the one or more on-call artificial intelligence agents (e.g., one or more on-call agents) is driven by a respective computational component.

(D15-a) In some embodiments of D1-a to D14-a, the respective computational component includes at least one of the group consisting of (i) an analytical model, (ii) a large-language model, and (iii) a plugin.

650 652 (D15-b) In some embodiments of D1-b to D14-b, each artificial intelligence agent of the interface coordinating artificial intelligence agent (e.g., coordinating agent) and the one or more on-call artificial intelligence agents (e.g., one or more on-call agents) includes an analytical model or a plugin.

630 632 400 4 FIG. (D16-a) In some embodiments of D1-a to D15-a, the receiving the incidentand the transmitting the output dataare performed in a graphical portal (e.g., example UIin).

630 632 400 4 FIG. (D16-b) In some embodiments of D1-b to D15-b, the receiving the critical computing incident (e.g., incident) and the transmitting the output dataare performed in a graphical portal (e.g., example UIin).

(E1-a) In accordance with some embodiments, a computer system includes one or more processors memory storing one or more programs. The one or more programs are configured to be executed by the one or more processors. The one or more programs include instructions for performing the method of any of D1-a to D16-a.

(E1-b) In accordance with some embodiments, a computer system includes one or more processors memory storing one or more programs. The one or more programs are configured to be executed by the one or more processors. The one or more programs include instructions for performing the method of any of D1-b to D16-b.

(F1-a) A non-transitory computer readable storage medium storing one or more programs. The one or more programs include instructions that, when executed by a computer system that includes one or more processors, cause the one or more processors to perform the method of any of D1-a to D16-a.

(F1-b) A non-transitory computer readable storage medium storing one or more programs. The one or more programs include instructions that, when executed by a computer system that includes one or more processors, cause the one or more processors to perform the method of any of D1-b to D16-b.

11 FIG. 2 FIG. 2 FIG. 1100 1100 200 1100 210 is a flow diagram illustrating a methodof orchestrating agents for self-service, in accordance with some embodiments. The methodmay be performed at a computer system (e.g., the computer system,) having one or more processors and memory storing instructions for execution by the one or more processors. In some embodiments, the methodis performed by executing instructions stored in memory (e.g., memory,) of the computer system.

In some embodiments, each of the agents described below is an artificial intelligence agent. In some embodiments, each of the agents described below includes an LLM. In some embodiments, each of the events described below is a critical event (e.g., associated with critical and high-priority incidents) and requires computation (e.g., real-time user/incident data analysis, code script generations, resource-intensive computations/inquiries, etc.).

1100 1102 750 1 702 730 1 706 712 710 714 1100 730 1 1104 750 2 732 710 1100 1106 750 1 702 732 706 1100 1108 750 1 702 730 2 706 710 1100 730 2 1110 750 2 738 710 1100 1112 750 1 702 738 706 (G1-a) The methodincludes receiving (operation), by an interface agent-and via a web user interface, a first user query-from a userthat defines a request to summarize historical datacorresponding to a critical eventassociated with a plurality of incidents. The methodfurther includes in response to receiving the first user query-, generating (operation), by an executing agent-, an event reportassociated with the critical event. The methodfurther includes displaying (operation), by the interface agent-and via the web user interface, the event reportto the user. The methodfurther includes receiving (operation), by the interface agent-and via the web user interface, a second user query-from the userthat defines a request to reduce a mean time to repair (MTTR) for resolving the critical event. The methodfurther includes in response to receiving the second user query-, generating (operation), by the executing agent-, an enhanced standard operating procedure (SOP)configured to reduce the MTTR for resolving the critical event. The methodfurther includes displaying (operation), by the interface agent-and via the web user interface, the enhanced SOPto the user.

1100 750 1 702 730 1 706 712 710 714 1100 730 1 750 2 732 710 1100 750 1 702 732 706 1100 750 1 702 730 2 706 710 1100 730 2 750 2 738 710 1100 750 1 702 738 706 750 1 750 2 (G1-b) In some embodiments, the methodincludes receiving, by an interface artificial intelligence agent (e.g., interface agent-) and via a web user interface, a first user query-from a userthat defines a request to summarize historical datacorresponding to a critical computing event (e.g., critical event) associated with a plurality of computing incidents (e.g., plurality of incidents). The methodfurther includes in response to receiving the first user query-, generating, by an executing artificial intelligence agent (e.g., executing agent-), an event reportassociated with the critical computing event (e.g., critical event). The methodfurther includes displaying, by the interface artificial intelligence agent (e.g., interface agent-) and via the web user interface, the event reportto the user. The methodfurther includes receiving, by the interface artificial intelligence agent (e.g., interface agent-) and via the web user interface, a second user query-from the userthat defines a request to reduce a mean time to repair (MTTR) for resolving the critical computing event (e.g., critical event). The methodfurther includes in response to receiving the second user query-, generating, by the executing artificial intelligence agent (e.g., executing agent-), an enhanced standard operating procedure (SOP)configured to reduce the MTTR for resolving the critical computing event (e.g., critical event). The methodfurther includes displaying, by the interface artificial intelligence agent (e.g., interface agent-) and via the web user interface, the enhanced SOPto the user. Each artificial intelligence agent of the interface artificial intelligence agent (e.g., interface agent-) and the executing artificial intelligence agent (e.g., executing agent-) is distinct from the other and includes a large-language model.

712 716 716 1 716 716 1 716 714 1 714 k (G2-a) In some embodiments of G1-a, the historical dataincludes a plurality of SOPs(e.g., SOP-to SOP-, where k is an integer greater than two). Each (e.g., SOP-) of plurality of SOPsis associated with a corresponding incident (e.g., incident-) of the plurality of incidents.

712 716 716 1 716 716 1 716 714 1 714 k (G2-b) In some embodiments of G1-b, the historical dataincludes a plurality of SOPs(e.g., SOP-to SOP-, where k is an integer greater than two). Each (e.g., SOP-) of plurality of SOPsis associated with a corresponding computing incident (e.g., incident-) of the plurality of computing incidents (e.g., plurality of incidents).

712 718 718 1 718 718 1 718 714 1 714 k (G3-a) In some embodiments of G1-a to G2-a, the historical dataincludes a plurality of incident logs(e.g., incident log-to incident log-, where k is an integer greater than two). Each (e.g., incident log-) of the plurality of incident logsis associated with a corresponding incident (e.g., incident-) of the plurality of incidentsand has a corresponding resolution history.

712 718 1 718 718 1 718 714 1 714 k (G3-b) In some embodiments of G1-b to G2-b, the historical dataincludes a plurality of computing incident logs (e.g., incident log-to incident log-, where k is an integer greater than two). Each (e.g., incident log-) of the plurality of computing incident logs (e.g., incident logs) is associated with a corresponding computing incident (e.g., incident-) of the plurality of computing incidents (e.g., incidents) and has a corresponding resolution history.

730 1 750 2 732 710 750 1 730 1 750 2 750 2 730 1 712 704 750 2 732 712 750 2 732 750 1 (G4-a) In some embodiments of G1-a to G3-a, in response to receiving the first user query-, generating, by the executing agent-, the event reportassociated with the critical eventincludes transmitting, by the interface agent-, the first user query-to the executing agent-; retrieving, by the executing agent-and based on the first user query-, the historical datafrom a repository database; generating, by the executing agent-, the event reportto summarize the historical data; and sending, by the executing agent-, the event reportto the interface agent-.

730 1 750 2 732 710 750 1 730 1 750 2 750 2 730 1 712 704 750 2 732 712 750 2 732 750 1 (G4-b) In some embodiments of G1-b to G3-b, in response to receiving the first user query-, generating, by the executing artificial intelligence agent (e.g., executing agent-), the event reportassociated with the critical computing event (e.g., critical event) includes transmitting, by the interface artificial intelligence agent (e.g., interface agent-), the first user query-to the executing artificial intelligence agent (e.g., executing agent-); retrieving, by the executing artificial intelligence agent (e.g., executing agent-) and based on the first user query-, the historical datafrom a repository database; generating, by the executing artificial intelligence agent (e.g., executing agent-), the event reportto summarize the historical data; and transmitting, by the executing artificial intelligence agent (e.g., executing agent-), the event reportto the interface artificial intelligence agent (e.g., interface agent-).

730 2 750 2 738 710 750 1 730 2 750 2 750 2 730 2 712 738 710 750 2 738 750 1 (G5-a) In some embodiments of G1-a to G4-a, in response to receiving the second user query-, generating, by the executing agent-, the enhanced SOPconfigured to reduce the MTTR for resolving the critical eventincludes: transmitting, by the interface agent-, the second user query-to the executing agent-; analyzing, by the executing agent-and based on the second user query-, the historical datato generate the enhanced SOPconfigured to reduce the MTTR for resolving the critical event; and sending, by the executing agent-, the enhanced SOPto the interface agent-.

730 2 750 2 738 710 750 1 730 2 750 2 750 2 730 2 712 738 710 750 2 738 750 1 (G5-b) In some embodiments of G1-b to G4-b, in response to receiving the second user query-, generating, by the executing artificial intelligence agent (e.g., executing agent-), the enhanced SOPconfigured to reduce the MTTR for resolving the critical computing event (e.g., critical event) includes: transmitting, by the interface artificial intelligence agent (e.g., interface agent-), the second user query-to the executing artificial intelligence agent (e.g., executing agent-); analyzing, by the executing artificial intelligence agent (e.g., executing agent-) and based on the second user query-, the historical datato generate the enhanced SOPconfigured to reduce the MTTR for resolving the critical computing event (e.g., critical event); and transmitting, by the executing artificial intelligence agent (e.g., executing agent-), the enhanced SOPto the interface artificial intelligence agent (e.g., interface agent-).

738 740 738 712 750 2 740 (G6-a) In some embodiments of G1-a to G5-a, the enhanced SOPincludes a code scriptconfigured to generate a textual SOP corresponding to the enhanced SOP. Analyzing the historical dataincludes validating, by the executing agent-, the code scriptto minimize errors.

738 740 738 712 750 2 740 (G6-b) In some embodiments of G1-b to G5-b, the enhanced SOPincludes a code scriptconfigured to generate a textual SOP corresponding to the enhanced SOP. Analyzing the historical dataincludes validating, by the artificial intelligence executing agent (e.g., executing agent-), the code scriptto minimize errors.

750 2 650 652 650 6 FIG. 6 FIG. 6 FIG. (G7-a) In some embodiments of G1-a to G6-a, the executing agent-includes a coordinating agent (e.g., coordinating agentin) and one or more on-call agents (e.g., one or more on-call agentsin) dynamically spawned by the coordinating agent (e.g., coordinating agentin).

750 2 650 652 650 104 6 FIG. 6 FIG. 6 FIG. 1 FIG. (G7-b) In some embodiments of G1-b to G6-b, the executing artificial intelligence agent (e.g., executing agent-) includes an interface coordinating artificial intelligence agent (e.g., coordinating agentin) and one or more on-call artificial intelligence agents (e.g., one or more on-call agentsin) dynamically spawned by the interface coordinating artificial intelligence agent (e.g., coordinating agentin) using computational resources (e.g., resource of functional platformsin).

750 1 750 2 (G8-a) In some embodiments of G1-a to G7-a, each agent of the interface agent-and the executing agent-is driven by a respective computational component.

750 1 750 2 750 2 (G8-b) In some embodiments of G1-b to G7-b, each artificial intelligence agent of the interface artificial intelligence agent (e.g., interface agent-) and the executing artificial intelligence agent-(e.g., executing agent-) is driven by a respective computational component.

(G9-a) In some embodiments of G1-a to G8-a, the respective computational component includes at least one of the group consisting of (i) an analytical model, (ii) a large-language model, and (iii) a plugin.

750 1 750 2 (G9-b) In some embodiments of G1-b to G8-b, each artificial intelligence agent of the interface artificial intelligence agent (e.g., interface agent-) and the executing artificial intelligence agent (e.g., executing agent-) includes an analytical model or a plugin.

(H1-a) In accordance with some embodiments, a computer system includes one or more processors memory storing one or more programs. The one or more programs are configured to be executed by the one or more processors. The one or more programs include instructions for performing the method of any of G1-a to G9-a.

(H1-b) In accordance with some embodiments, a computer system includes one or more processors memory storing one or more programs. The one or more programs are configured to be executed by the one or more processors. The one or more programs include instructions for performing the method of any of G1-b to G9-b.

(I1-a) A non-transitory computer readable storage medium storing one or more programs. The one or more programs include instructions that, when executed by a computer system that includes one or more processors, cause the one or more processors to perform the method of any of G1-a to G9-a.

(I1-b) A non-transitory computer readable storage medium storing one or more programs. The one or more programs include instructions that, when executed by a computer system that includes one or more processors, cause the one or more processors to perform the method of any of G1-b to G9-b.

9 11 FIGS.- Althoughillustrate a number of logical stages in a particular order, stages which are not order dependent may be reordered and other stages may be combined or broken out. Some reordering or other groupings not specifically mentioned will be apparent to those of ordinary skill in the art, so the ordering and groupings presented herein are not exhaustive. Moreover, it should be recognized that the stages could be implemented in hardware, firmware, software, or any combination thereof.

The foregoing description, for purpose of explanation, has been described with reference to specific embodiments. However, the illustrative discussions above are not intended to be exhaustive or to limit the embodiments to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. The embodiments were chosen and described in order to best explain the principles and their practical applications, to thereby enable others skilled in the art to best utilize the embodiments and various embodiments with various modifications as are suited to the particular use contemplated.